© 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. 57998
    Prev
    Next
    INDEX
    Explanations

    and / in copyright text

    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
     scratching
    -0.69
     Nutzungs
    -0.68
    Противо
    -0.65
     drawings
    -0.64
    ネマ
    -0.63
     противо
    -0.62
     Edizioni
    -0.61
     actions
    -0.60
     furthering
    -0.60
    Ghana
    -0.60
    POSITIVE LOGITS
    rye
    0.77
    ffers
    0.74
     Kav
    0.74
     COACH
    0.73
    kav
    0.72
    ClickListener
    0.72
    yng
    0.71
    cpt
    0.71
    antro
    0.70
    oree
    0.69
    Activations Density 0.060%

    No Known Activations