© 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. 129316
    Prev
    Next
    INDEX
    Explanations

    loop counters `i`

    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
     that
    -1.22
     reciclado
    -0.95
     jaunes
    -0.91
     recepción
    -0.90
     bicara
    -0.90
     enfermera
    -0.89
    Analyte
    -0.88
     Obtenez
    -0.87
    ྂ
    -0.86
    bản
    -0.85
    POSITIVE LOGITS
     ഒരു
    1.11
    Ирина
    1.11
     lucre
    0.98
    irmingham
    0.95
     mélange
    0.94
     gratific
    0.93
     hilar
    0.92
    ::{
    0.90
     Remake
    0.90
    ètre
    0.89
    Activations Density 0.003%

    No Known Activations