© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123497
    Prev
    Next
    INDEX
    Explanations

    financial transactions and dates

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

    numerical contexts and calculations

    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
     exuber
    0.50
     indispensables
    0.49
    സി
    0.48
    ট্ট
    0.46
     vybaven
    0.45
    <0x0D>
    0.44
     egz
    0.43
     mph
    0.43
     وسي
    0.43
     vich
    0.43
    POSITIVE LOGITS
    drawString
    0.52
    विज्ञापन
    0.51
     हुईं
    0.48
    maktadır
    0.48
    伸手
    0.47
    awarkan
    0.46
    addSprite
    0.45
     संगम
    0.45
    錒
    0.44
    ással
    0.43
    Activations Density 0.000%

    No Known Activations