© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36541
    Prev
    Next
    INDEX
    Explanations

    configuration parameters or file paths

    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
    ----------------
    -1.00
     on
    -0.98
    >'+
    -0.93
    EL
    -0.92
    <eos>
    -0.90
    ২
    -0.88
     those
    -0.88
    也会
    -0.87
     what
    -0.87
    ER
    -0.85
    POSITIVE LOGITS
     restantes
    1.04
     écla
    0.96
    rotten
    0.96
    Kde
    0.94
    extendable
    0.94
     ancianos
    0.94
     Njema
    0.94
     reembols
    0.93
    Largeur
    0.93
     ressort
    0.93
    Activations Density 0.012%

    No Known Activations