© 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. 330
    Prev
    Next
    INDEX
    Explanations

    location or object features

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

    instructions, requirements, and requests

    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
     क्षेत्र
    0.42
     बारा
    0.41
     హైద
    0.41
    ວິ
    0.41
     ஆண்டுகளுக்கு
    0.40
    कन्या
    0.40
    ൪
    0.40
    liği
    0.39
    ²',
    0.39
     houve
    0.39
    POSITIVE LOGITS
    .”
    0.48
    .)
    0.45
    ).
    0.43
     If
    0.43
    ."
    0.43
    ".
    0.42
     
    0.42
     but
    0.41
     while
    0.41
    .
    0.41
    Activations Density 0.547%

    No Known Activations