© 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. 56807
    Prev
    Next
    INDEX
    Explanations

    CT state

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

    explains meaning and concepts

    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
    u
    0.59
    ok
    0.58
    ons
    0.56
     in
    0.55
    k
    0.54
    ut
    0.53
    fu
    0.53
    x
    0.53
    ate
    0.52
    z
    0.52
    POSITIVE LOGITS
    嫚
    0.62
    价值观
    0.57
     버전
    0.56
    壹百
    0.53
     церков
    0.53
     британ
    0.53
    诌
    0.52
     قدیمی
    0.51
     Брита
    0.51
    笵
    0.51
    Activations Density 0.000%

    No Known Activations