© 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. 182290
    Prev
    Next
    INDEX
    Explanations

    list items/phrases

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

    formatting and technical terms

    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
    precipitation
    0.46
    n
    0.46
     colorless
    0.45
    normalized
    0.45
     correspondent
    0.43
    ｛
    0.43
     admissible
    0.42
    acional
    0.41
    policy
    0.41
    mean
    0.41
    POSITIVE LOGITS
     Vanderbilt
    0.55
    깽
    0.49
     الحصول
    0.49
    வாய
    0.48
    蚪
    0.47
     Hailey
    0.46
     Grundstück
    0.46
    伊斯
    0.46
    燬
    0.46
    <unused564>
    0.46
    Activations Density 0.000%

    No Known Activations