© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12851
    Prev
    Next
    INDEX
    Explanations

    repository path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     городских
    0.46
    ᱙
    0.45
    жном
    0.42
    ጕ
    0.41
    轳
    0.41
     adolescents
    0.40
    
    0.40
    杽
    0.40
     digestibility
    0.40
     simplicity
    0.40
    POSITIVE LOGITS
     Union
    0.44
    idges
    0.43
    ale
    0.40
    ana
    0.40
    غام
    0.39
     strike
    0.39
     Ultimate
    0.39
    er
    0.38
    Union
    0.38
     Firm
    0.38
    Activations Density 0.000%

    No Known Activations