© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 17844
    Prev
    Next
    INDEX
    Explanations

    date ranges or periods

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

    ranges and delimiters

    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
    ेलकम
    0.43
    <unused1112>
    0.42
    ्युअर
    0.39
     }(\
    0.39
    :"))
    0.39
     ख़ु
    0.38
    𝓌
    0.38
    ُن
    0.38
    PlistBuddy
    0.37
    ългар
    0.37
    POSITIVE LOGITS
     onwards
    0.96
    부터
    0.95
     മുതൽ
    0.94
     മുതല്‍
    0.82
    –
    0.80
     έως
    0.77
    至
    0.77
     onward
    0.76
    到
    0.73
     až
    0.71
    Activations Density 0.129%

    No Known Activations