© 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. 48993
    Prev
    Next
    INDEX
    Explanations

    variable and index access

    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
     should
    -1.02
     if
    -0.99
     on
    -0.97
     is
    -0.96
    思議
    -0.96
    TextUtils
    -0.92
     to
    -0.90
     with
    -0.86
    usul
    -0.85
     though
    -0.84
    POSITIVE LOGITS
     بعضی
    1.05
    らなかった
    1.02
     deme
    1.02
    蕖
    1.01
    [](
    1.01
    toString
    1.00
    valueOf
    1.00
    erschein
    0.97
     voiture
    0.96
     彼女
    0.95
    Activations Density 0.044%

    No Known Activations