© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80051
    Prev
    Next
    INDEX
    Explanations

    runningnation price dayscompany

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    howto
    0.49
    ždy
    0.48
    ﺷ
    0.48
    సిన
    0.47
     አሉ
    0.46
    边
    0.46
    ారి
    0.45
    溸
    0.45
    াবু
    0.45
    诈
    0.45
    POSITIVE LOGITS
    in
    0.48
     recog
    0.46
    unlike
    0.44
     norske
    0.44
    ાદ
    0.43
    1
    0.43
     llega
    0.42
     ose
    0.42
     privilegio
    0.42
    ната
    0.42
    Activations Density 0.013%

    No Known Activations