© 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. 153430
    Prev
    Next
    INDEX
    Explanations

    consulting about criminal matters

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

    actionable predictions

    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
     was
    0.55
    was
    0.50
     Ն
    0.49
    Í
    0.48
    分岐
    0.47
    était
    0.45
    Dij
    0.45
    oz
    0.44
    iesel
    0.44
    є
    0.44
    POSITIVE LOGITS
     outspoken
    0.49
     актер
    0.48
    公开
    0.47
    வதால்
    0.44
     публи
    0.44
    主演
    0.44
     ủng
    0.43
    你在
    0.43
    性と
    0.42
    诗人
    0.41
    Activations Density 0.000%

    No Known Activations