© 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. 10-GEMMASCOPE-RES-131K
    7. 128927
    Prev
    Next
    INDEX
    Explanations

    DEPTH, Dyspnea, Introduction, Q:, verbal memory

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

    the specific numeric token “16.”

    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
     hatta
    -1.56
     görüntüsü
    -1.56
    Questão
    -1.55
     MUNDO
    -1.50
     or
    -1.46
    moderne
    -1.44
     çay
    -1.43
     milyon
    -1.43
     heeft
    -1.42
    artik
    -1.41
    POSITIVE LOGITS
     was
    2.28
     is
    2.06
     Its
    1.69
     were
    1.61
     His
    1.38
     its
    1.38
    </td>
    1.32
    by
    1.31
     gän
    1.30
    来到了
    1.27
    Activations Density 0.000%

    No Known Activations