© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64733
    Prev
    Next
    INDEX
    Explanations

    provide you a response

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

    The neuron fires strongly on first‐person “we” or “I” statements offering or promising actions (e.g. “we will,” “we can,” “I can give you”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ویکی‌پدیای
    -1.09
     ALWAYS
    -1.04
     Japão
    -1.02
    movieId
    -0.98
     at
    -0.95
    část
    -0.94
     exercício
    -0.94
    kuwa
    -0.94
     réus
    -0.93
    heren
    -0.93
    POSITIVE LOGITS
     you
    1.91
     then
    1.48
     odpowied
    1.27
     вам
    1.16
     your
    1.16
    蛳
    1.11
     entsprechenden
    1.08
    給你
    1.07
     them
    1.06
    then
    1.05
    Activations Density 0.023%

    No Known Activations