© 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. 34-GEMMASCOPE-RES-131K
    7. 31511
    Prev
    Next
    INDEX
    Explanations

    JavaScript code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    sieur
    -1.16
    teos
    -1.10
    dich
    -1.09
     filós
    -1.09
     europeos
    -1.09
    瘠
    -1.08
    ristmas
    -1.08
    aucune
    -1.05
    sene
    -1.04
     этого
    -1.03
    POSITIVE LOGITS
    else
    1.12
     with
    1.09
     still
    1.05
    导弹
    1.04
     as
    1.03
     may
    0.92
     during
    0.91
    Ns
    0.90
     unquestionably
    0.88
    ze
    0.88
    Activations Density 0.010%

    No Known Activations