© 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. 34192
    Prev
    Next
    INDEX
    Explanations

    product names

    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
     эффектив
    -0.98
    asi
    -0.98
     beeinf
    -0.96
     niitä
    -0.96
     encantador
    -0.94
    钱包
    -0.94
     опас
    -0.94
    ându
    -0.93
     estético
    -0.92
    ところに
    -0.92
    POSITIVE LOGITS
     is
    1.13
     experience
    1.10
     that
    1.09
     we
    1.01
     I
    1.00
     you
    0.96
    kussion
    0.94
     in
    0.91
     andra
    0.91
     competi
    0.90
    Activations Density 0.053%

    No Known Activations