© 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. 18555
    Prev
    Next
    INDEX
    Explanations

    lists or quantities

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

    file name or code snippet context

    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
     a
    0.79
    A
    0.64
    O
    0.58
    <unused60>
    0.56
    ELL
    0.56
    a
    0.56
    För
    0.54
    Biden
    0.54
    Hector
    0.54
    魏
    0.54
    POSITIVE LOGITS
     for
    0.89
    도
    0.81
     in
    0.66
     σε
    0.65
    น
    0.65
    ও
    0.65
     در
    0.57
    在
    0.56
    ர்
    0.55
     geolocation
    0.55
    Activations Density 0.254%

    No Known Activations