© 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. 93017
    Prev
    Next
    INDEX
    Explanations

    scanned-page documents

    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
     گیرد
    -1.02
    warzys
    -1.01
     meste
    -0.91
     PUSTAKA
    -0.90
    gunas
    -0.90
    AlreadyExists
    -0.90
     bré
    -0.90
    ]--;
    -0.88
    {-\
    -0.87
    ЙТЕ
    -0.87
    POSITIVE LOGITS
     this
    1.01
    <h1>
    0.96
    <eos>
    0.93
     Arbeitnehmer
    0.92
     these
    0.92
    Appendix
    0.90
    誦
    0.90
     Appendix
    0.89
    imetry
    0.87
     encontraban
    0.87
    Activations Density 0.002%

    No Known Activations