© 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. 40443
    Prev
    Next
    INDEX
    Explanations

    people and humans

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

    the neuron tends to pick out words that name the thing being acted on—i.e. the direct object or “patient” of an action.

    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
     ('
    -1.10
     own
    -1.07
    を変更
    -1.06
    犧
    -1.05
    給你
    -1.02
     respek
    -1.02
    '
    -1.02
    rago
    -0.99
     публикации
    -0.99
    摄像
    -0.98
    POSITIVE LOGITS
    atzes
    1.10
     comod
    1.09
     they
    1.09
    peicher
    1.09
    ználat
    1.08
    SupportActionBar
    1.07
    tonsoft
    1.06
    不舒服
    1.05
    olá
    1.05
    ieniu
    1.04
    Activations Density 0.169%

    No Known Activations