© 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. 162010
    Prev
    Next
    INDEX
    Explanations

    pipeline infrastructure

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

    levels or scales

    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
     者
    0.54
    決済
    0.48
     şeyi
    0.47
     nghĩa
    0.44
    گذار
    0.43
    /(:
    0.43
    に適
    0.42
     župan
    0.42
    ತಕ್ಕ
    0.42
     dispositions
    0.42
    POSITIVE LOGITS
    ુ
    0.50
    ン
    0.49
    il
    0.49
    on
    0.48
    िल्स
    0.47
    em
    0.47
    heil
    0.46
    FOLLOW
    0.45
    WORLD
    0.45
    uacao
    0.45
    Activations Density 0.001%

    No Known Activations