© 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. 31716
    Prev
    Next
    INDEX
    Explanations

    sir 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
    يتر
    -0.80
    ℤ
    -0.80
    Welsh
    -0.79
    导
    -0.77
    好久
    -0.77
     Get
    -0.77
    Senator
    -0.76
     Tek
    -0.74
    住宿
    -0.73
    сков
    -0.73
    POSITIVE LOGITS
     Kinders
    1.06
     Græ
    0.88
     Chol
    0.87
    adah
    0.86
    準
    0.85
     mettez
    0.84
     commonplace
    0.82
     ecclesiastical
    0.81
    けれ
    0.81
    loyees
    0.81
    Activations Density 0.099%

    No Known Activations