© 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. 148746
    Prev
    Next
    INDEX
    Explanations

    service provider, at least three

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

    spacetime itself

    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
    自己的
    0.45
    对
    0.45
    帮
    0.45
     resultMap
    0.45
    毕业
    0.44
     თუ
    0.44
     对
    0.44
     وك
    0.43
     отчет
    0.43
     исследование
    0.43
    POSITIVE LOGITS
    slaught
    0.48
     ablaze
    0.44
    dispers
    0.44
    ುತ್ತವೆ
    0.43
     cavalry
    0.43
     glace
    0.42
    CIRCLE
    0.42
     خم
    0.42
     WHICH
    0.42
    granted
    0.41
    Activations Density 0.000%

    No Known Activations