© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141665
    Prev
    Next
    INDEX
    Explanations

    to learn, start by, friendly ice, the first, nothing less

    np_acts-logits-general · gemini-2.5-flash-lite

    detergent pods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     komb
    0.50
     skorzyst
    0.50
    娌
    0.49
     fejleszt
    0.47
     Kombat
    0.47
    历
    0.47
    terweight
    0.46
     korzyst
    0.46
     favorit
    0.46
    estry
    0.45
    POSITIVE LOGITS
     بڑے
    0.47
    чами
    0.46
    мами
    0.45
    тами
    0.44
     تام
    0.44
    <0x80>
    0.43
    ای
    0.43
    никами
    0.43
     normed
    0.42
    低い
    0.41
    Activations Density 0.001%

    No Known Activations