© 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. 81505
    Prev
    Next
    INDEX
    Explanations

    crisis has

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

    service management

    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
     zullen
    0.49
     chaise
    0.44
    lumin
    0.42
     Inheritance
    0.42
     grosso
    0.42
    箫
    0.42
     prelude
    0.41
     junit
    0.41
    FindFirst
    0.41
    জিস্ট
    0.41
    POSITIVE LOGITS
    否
    0.50
    歯
    0.50
    喉
    0.48
    事は
    0.48
    視
    0.48
     perpetually
    0.47
    才能
    0.47
    密度
    0.46
    得
    0.46
    не
    0.46
    Activations Density 0.000%

    No Known Activations