© 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. 29805
    Prev
    Next
    INDEX
    Explanations

    request and contract implications

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

    category initializers

    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
     Mujhe
    0.50
     ਪ
    0.50
     Pued
    0.49
    ਾ
    0.49
     वायू
    0.49
     හා
    0.48
     જુ
    0.48
    ulik
    0.46
    onie
    0.46
     બ
    0.46
    POSITIVE LOGITS
     entretenimiento
    0.50
    ibr
    0.50
    뭉
    0.48
    Subscriptions
    0.46
    साइ
    0.46
    まだまだ
    0.45
    министра
    0.44
    嶋
    0.44
    낑
    0.44
    一条
    0.44
    Activations Density 0.000%

    No Known Activations