© 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. 13058
    Prev
    Next
    INDEX
    Explanations

    localhost:port

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

    localhost:port

    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
    Raquete
    0.56
    📫
    0.54
     actualidad
    0.49
     inoxyd
    0.49
    PERATURE
    0.48
    敝
    0.48
     необходимость
    0.48
     ويكيپيديا
    0.46
     bilir
    0.46
     solides
    0.46
    POSITIVE LOGITS
     with
    0.62
    /
    0.60
    with
    0.53
    id
    0.53
    5
    0.52
     (
    0.51
    v
    0.51
     localhost
    0.50
    localhost
    0.48
    db
    0.48
    Activations Density 0.002%

    No Known Activations