© 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. 35109
    Prev
    Next
    INDEX
    Explanations

    density and estimation

    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
    cześ
    0.44
    aży
    0.43
     frequência
    0.43
    ꞎ
    0.43
     प्रजनन
    0.41
    ått
    0.41
    ológicos
    0.40
     llevo
    0.40
     wcześniej
    0.40
     hasattr
    0.39
    POSITIVE LOGITS
     COLOR
    0.48
    の
    0.46
    ﾕ
    0.46
    ек
    0.44
    <0xEF>
    0.44
     двох
    0.44
     во
    0.44
    ד
    0.44
    elerde
    0.43
    를
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.