© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45679
    Prev
    Next
    INDEX
    Explanations

    security and policy details

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

    avoiding conflict, simulator experience, less hype

    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
    తుంది
    0.49
    a
    0.48
    i
    0.48
     দিয়েছিলেন
    0.46
    jub
    0.46
    蓝色
    0.42
     bandwidth
    0.42
    授予
    0.42
     SCA
    0.41
    ㄴ
    0.41
    POSITIVE LOGITS
     ফ
    0.47
     electrónica
    0.46
     пробле
    0.46
     combate
    0.45
     militares
    0.45
    enske
    0.45
     persec
    0.44
    кат
    0.44
     российский
    0.44
    𝘧
    0.44
    Activations Density 0.000%

    No Known Activations