© 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. 198675
    Prev
    Next
    INDEX
    Explanations

    attachments and citations

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

    platform

    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
    Negative Logits
     sogar
    0.47
     to
    0.45
     명
    0.43
     gente
    0.42
    OV
    0.42
     bestowed
    0.42
     스마트
    0.42
     permanent
    0.41
     itin
    0.41
     dode
    0.41
    POSITIVE LOGITS
    pointA
    0.54
    tà
    0.52
    attachments
    0.49
    attachment
    0.48
    왁
    0.48
    푯
    0.47
    quartz
    0.46
    सत्ता
    0.46
    ا
    0.46
    ह
    0.46
    Activations Density 0.000%

    No Known Activations