© 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. 27814
    Prev
    Next
    INDEX
    Explanations

    `.` followed by file extensions or code elements

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

    file extensions and code syntax

    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
    న్
    0.65
    кі
    0.61
    to
    0.58
    槅
    0.57
     भाष
    0.56
     matin
    0.55
     hypothes
    0.55
    確認
    0.55
    絊
    0.54
     tých
    0.54
    POSITIVE LOGITS
     (.
    0.85
    htaccess
    0.75
     [.
    0.75
    ese
    0.72
    [.
    0.70
     $.
    0.69
    ες
    0.68
    jobj
    0.68
     .$
    0.66
    hle
    0.66
    Activations Density 0.071%

    No Known Activations