© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41170
    Prev
    Next
    INDEX
    Explanations

    thinking of or about

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on first-person introspective lead-ins expressing personal intention or consideration (e.g. “I’m thinking of…,” “I’m expecting…”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    statements where the writer expresses they are thinking about or considering something (contemplation/planning).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the phrase "I'm thinking" or "I am thinking" followed by "of" or "about".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jestel
    -1.63
     diseñados
    -1.59
     abiertos
    -1.58
     seleccionados
    -1.58
    ohjel
    -1.52
    estões
    -1.52
    ซึ่ง
    -1.52
     使っ
    -1.49
     deberes
    -1.48
    𝕿
    -1.48
    POSITIVE LOGITS
     about
    2.23
     also
    2.03
    
    1.71
     something
    1.59
     moves
    1.55
    日本的
    1.55
    al
    1.52
    ，，
    1.47
    Также
    1.46
    𞤤
    1.46
    Activations Density 0.008%

    No Known Activations