© 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. 34-GEMMASCOPE-RES-131K
    7. 63274
    Prev
    Next
    INDEX
    Explanations

    code punctuation and operators

    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_34/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
     publiques
    -0.94
     equipada
    -0.87
     serii
    -0.85
     balení
    -0.85
     legado
    -0.85
     passada
    -0.84
    wird
    -0.83
    🐔
    -0.82
     pacto
    -0.82
    kanal
    -0.81
    POSITIVE LOGITS
     Wyn
    0.86
     entire
    0.85
     Central
    0.82
     camer
    0.80
    fall
    0.79
    hai
    0.79
    oczes
    0.77
    )..
    0.77
    hopper
    0.77
     nuevamente
    0.76
    Activations Density 0.012%

    No Known Activations