© 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. 53053
    Prev
    Next
    INDEX
    Explanations

    bootstrapcdn font urls

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

    technical identifiers and paths

    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
     for
    0.89
     that
    0.79
    and
    0.79
    for
    0.77
     and
    0.72
    that
    0.71
    ↵↵
    0.70
    。
    0.70
    ’
    0.70
    had
    0.66
    POSITIVE LOGITS
     Tattha
    0.66
     ставак
    0.64
    镙
    0.63
    MyToolkit
    0.62
     ক্যাথোডে
    0.61
     striées
    0.60
    gmzy
    0.60
     Prothorax
    0.59
    ässer
    0.58
    ऊंगी
    0.58
    Activations Density 0.000%

    No Known Activations