© 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. 111325
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by articles

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

    The neuron flags, in each text snippet, the single most distinctive (i.e. highest–tf-idf-style) content word.

    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
     auténtica
    -1.76
     también
    -1.70
    了过来
    -1.70
     viviendo
    -1.69
    関する
    -1.57
     atentos
    -1.57
    痈
    -1.57
     listos
    -1.55
    ₱
    -1.55
     sosteniendo
    -1.53
    POSITIVE LOGITS
    3
    2.09
    1
    2.02
    8
    1.92
    0
    1.87
    4
    1.82
    2
    1.82
    莚
    1.75
    自己的
    1.73
    6
    1.73
    7
    1.72
    Activations Density 0.086%

    No Known Activations