© 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. 65492
    Prev
    Next
    INDEX
    Explanations

    code segments and technical terms

    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
    趿
    -1.06
    widual
    -1.00
    RTHOOK
    -1.00
    igel
    -1.00
     articula
    -1.00
    glBindBuffer
    -0.98
    €™
    -0.98
    meye
    -0.97
     cuatro
    -0.96
    ureusement
    -0.96
    POSITIVE LOGITS
     especializado
    1.00
    Sunflower
    0.96
     jų
    0.93
     countries
    0.90
     rodeado
    0.89
     stately
    0.87
    ;
    0.86
     if
    0.85
     comprometido
    0.85
    Facile
    0.84
    Activations Density 0.260%

    No Known Activations