© 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. 19362
    Prev
    Next
    INDEX
    Explanations

    romance, execute, stones, time, Nike

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

    Screen, Bitmap, Update

    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
    ütz
    0.39
    unay
    0.36
    ൫
    0.36
     л
    0.35
     Ultrasound
    0.35
    ್
    0.35
     ricord
    0.34
    在那里
    0.34
     एक्ट्रेस
    0.34
     letz
    0.33
    POSITIVE LOGITS
    $.;
    0.45
     gặp
    0.45
     ከተ
    0.43
     cán
    0.41
    $;
    0.41
     встре
    0.40
    $-,
    0.40
    Compras
    0.38
     sociedades
    0.38
    ";//
    0.37
    Activations Density 0.000%

    No Known Activations