© 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. 86951
    Prev
    Next
    INDEX
    Explanations

    emergencies are, rare books, audience about

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

    not with grand

    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
    c
    0.43
     .
    0.42
     netting
    0.42
    નુ
    0.42
    ។
    0.41
     apostles
    0.41
     Ако
    0.41
    قط
    0.41
    حه
    0.41
    CTT
    0.40
    POSITIVE LOGITS
     მხოლოდ
    0.50
    ≖
    0.47
    装備
    0.46
    시설
    0.46
     जायें
    0.46
     아름
    0.46
     योद्धा
    0.46
    装备
    0.46
    设施
    0.46
     হুমকি
    0.46
    Activations Density 0.004%

    No Known Activations