© 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. 10-GEMMASCOPE-RES-131K
    7. 113103
    Prev
    Next
    INDEX
    Explanations

    instrument and its uses

    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_10/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
    떳
    -2.42
     unſ
    -2.36
    螣
    -2.28
    
    -2.28
    вгений
    -2.17
    تیجه
    -2.13
     是
    -2.11
    ઁ
    -2.09
    甞
    -2.06
    pidou
    -2.05
    POSITIVE LOGITS
    ли
    2.22
    餵
    2.17
    m
    2.11
     として
    2.08
     This
    2.08
     For
    2.02
     なら
    2.00
    ଽ
    1.99
    協助
    1.98
     instrument
    1.96
    Activations Density 0.014%

    No Known Activations