© 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. 68102
    Prev
    Next
    INDEX
    Explanations

    some sort of

    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
     visse
    -2.34
     nasce
    -2.20
     accol
    -2.17
    鵙
    -2.16
    
    -2.11
     elettrica
    -2.09
     certamente
    -2.06
    does
    -2.06
     タンク
    -2.06
    鸶
    -2.05
    POSITIVE LOGITS
     as
    2.38
     incorporate
    2.36
     an
    2.19
     substantial
    2.06
     find
    2.03
     including
    2.02
     promote
    2.02
     on
    2.02
     at
    2.00
     provide
    2.00
    Activations Density 0.009%

    No Known Activations