© 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. 34-GEMMASCOPE-RES-131K
    7. 76791
    Prev
    Next
    INDEX
    Explanations

    field names

    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
     over
    -0.89
     kvalit
    -0.78
     eyeing
    -0.78
    hyo
    -0.75
    /}{
    -0.73
    rister
    -0.73
    psic
    -0.72
    だよ
    -0.72
    crever
    -0.71
    🫘
    -0.71
    POSITIVE LOGITS
    earlier
    0.84
    Module
    0.83
    w
    0.82
     Modules
    0.80
     honorary
    0.78
    uvre
    0.77
     Mur
    0.77
     Dab
    0.76
    NOW
    0.75
    ılar
    0.75
    Activations Density 0.032%

    No Known Activations