© 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. 90645
    Prev
    Next
    INDEX
    Explanations

    items tagged

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

    safely contained

    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
    리아
    0.54
    offset
    0.52
    in
    0.51
    청
    0.48
    รา
    0.47
    ří
    0.47
     인수
    0.46
    부
    0.46
    กระจ
    0.46
    리스
    0.45
    POSITIVE LOGITS
    ፣
    0.59
     Онлайн
    0.55
     Unidas
    0.51
     Repert
    0.50
     Segunda
    0.50
     Sharif
    0.49
     Liquor
    0.48
     Bande
    0.47
     Propaganda
    0.47
     Doppio
    0.46
    Activations Density 0.000%

    No Known Activations