© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34846
    Prev
    Next
    INDEX
    Explanations

    digits followed by punctuation

    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
     polícia
    -1.16
     like
    -1.15
     would
    -1.12
     first
    -1.09
     but
    -1.04
     only
    -1.03
     mostly
    -0.98
    ул
    -0.97
     for
    -0.96
    gencias
    -0.94
    POSITIVE LOGITS
    desire
    1.02
    suddenly
    1.01
     gebaut
    0.98
     прокура
    0.96
    donde
    0.95
     panneaux
    0.93
     вже
    0.93
    decided
    0.93
     elevación
    0.92
    rsquo
    0.89
    Activations Density 0.001%

    No Known Activations