© 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. 241857
    Prev
    Next
    INDEX
    Explanations

    latest changes, someone had

    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
    ള്ളി
    0.45
    ть
    0.44
     Aeronaut
    0.44
     Vehicles
    0.43
     Carmen
    0.43
     Spiele
    0.43
     Servicios
    0.43
    푀
    0.42
    це
    0.42
    ुरु
    0.42
    POSITIVE LOGITS
    ASSERT
    0.46
    AUG
    0.46
     ប្រ
    0.46
    EMPT
    0.46
    s
    0.46
    shen
    0.45
    kts
    0.45
    UT
    0.45
    OT
    0.44
     ليش
    0.44
    Activations Density 0.000%

    No Known Activations