© 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. 25425
    Prev
    Next
    INDEX
    Explanations

    css properties and code lengths

    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
     ajuta
    -0.95
    Carreira
    -0.91
    ชา
    -0.90
     vė
    -0.89
     Sebastián
    -0.89
     pétrole
    -0.86
     ấn
    -0.86
     daarmee
    -0.86
     Viena
    -0.85
    нар
    -0.85
    POSITIVE LOGITS
     except
    0.93
     from
    0.91
    кров
    0.90
     because
    0.90
     a
    0.90
    usaha
    0.89
     rincón
    0.88
    ținut
    0.86
    åde
    0.86
    vein
    0.86
    Activations Density 0.020%

    No Known Activations