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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75197
    Prev
    Next
    INDEX
    Explanations

    i thought

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

    The neuron flags words and phrases that express personal cognition or mental state (e.g. “thought,” “knew,” “wondering,” “believe”).

    oai_token-act-pair · o4-miniTriggered 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
     other
    -1.77
     these
    -1.77
     their
    -1.68
     those
    -1.62
    に住
    -1.57
    骡
    -1.52
    vação
    -1.48
    最后由
    -1.48
     each
    -1.45
     spielte
    -1.45
    POSITIVE LOGITS
    '
    1.79
            
    1.77
     tetapi
    1.49
    9
    1.48
    8
    1.44
    ਲ਼
    1.44
     liked
    1.42
     joked
    1.41
    1
    1.41
    lossenen
    1.40
    Activations Density 0.055%

    No Known Activations