© 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. 22-GEMMASCOPE-RES-131K
    7. 33773
    Prev
    Next
    INDEX
    Explanations

    return statement, defaults

    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_22/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
    lewati
    -1.09
    hadapi
    -1.08
     gången
    -1.03
    eamiento
    -1.01
     mêmes
    -1.01
    pergillus
    -0.98
    旁边
    -0.97
    potentially
    -0.94
     publicités
    -0.94
     producteur
    -0.94
    POSITIVE LOGITS
     there
    1.07
     as
    0.92
    there
    0.90
     pilihan
    0.86
     There
    0.86
    There
    0.85
     Köl
    0.85
    ijoje
    0.84
     acara
    0.80
    زال
    0.80
    Activations Density 0.001%

    No Known Activations