© 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. 193173
    Prev
    Next
    INDEX
    Explanations

    service, termination, or discretionary actions

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

    describing analyses

    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
    គ្ន
    0.48
    奈
    0.46
     வள்ள
    0.43
    忽略
    0.42
     гимна
    0.42
    "?:
    0.42
     REGIUNI
    0.41
    Vide
    0.41
    держи
    0.41
    徘
    0.41
    POSITIVE LOGITS
     slang
    0.49
     gasto
    0.47
     *.
    0.46
     sintering
    0.46
    ेलर
    0.45
     timp
    0.44
     pharetra
    0.44
     uttering
    0.44
     😏
    0.44
    ED
    0.43
    Activations Density 0.001%

    No Known Activations