© 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. 90320
    Prev
    Next
    INDEX
    Explanations

    Repair Houston, Bridge Engineering, Spa, shut down

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

    code structure and programming concepts

    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
     reduced
    0.50
     Film
    0.50
     mitigated
    0.47
     witnessed
    0.47
     Cardiol
    0.47
     sensed
    0.46
    。
    0.45
     fresh
    0.45
    0.45
     reversed
    0.45
    POSITIVE LOGITS
    𒈬
    0.53
    slotBox
    0.53
     домаћинстава
    0.52
    GameState
    0.52
     使い
    0.51
    itabbo
    0.50
     கெல்வின்
    0.50
     حقی
    0.50
    サーバー
    0.50
    nań
    0.50
    Activations Density 0.001%

    No Known Activations