© 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. 174804
    Prev
    Next
    INDEX
    Explanations

    occasion, spells

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

    but preventable

    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
    ஸ
    0.51
    甠
    0.47
    лина
    0.46
    뜩
    0.46
    قيقة
    0.46
     supremely
    0.45
    μία
    0.45
    迵
    0.45
     blockbuster
    0.44
    ጣጠ
    0.44
    POSITIVE LOGITS
     east
    0.48
    !-
    0.47
     سرخ
    0.45
    の一つ
    0.44
    ymers
    0.44
     SER
    0.44
    dirs
    0.43
     beaches
    0.42
     TAYLOR
    0.42
     estuaries
    0.42
    Activations Density 0.000%

    No Known Activations