© 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. 135858
    Prev
    Next
    INDEX
    Explanations

    preceded by specific keywords

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

    calculate, split, vary, wafers, Tenants

    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
     lange
    0.52
     ο
    0.52
     长
    0.49
     Lookout
    0.48
     birth
    0.48
    ).
    0.47
     Ό
    0.47
     doctors
    0.46
     Gabriel
    0.46
     τις
    0.45
    POSITIVE LOGITS
    из
    0.49
    tried
    0.48
    ται
    0.47
    탤
    0.47
    ಾಯಕ
    0.47
    legd
    0.47
    대에
    0.45
    두
    0.44
    əd
    0.44
    dött
    0.44
    Activations Density 0.000%

    No Known Activations