© 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. 155393
    Prev
    Next
    INDEX
    Explanations

    foreign language identifiers

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

    companies, histories, reliable, desirable

    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
    Cong
    0.48
    Cash
    0.46
     Directions
    0.45
     Direction
    0.44
    A
    0.44
    Bread
    0.44
    Chois
    0.44
    Directions
    0.44
    Bush
    0.43
    begin
    0.42
    POSITIVE LOGITS
     ubicado
    0.55
    نیٹ
    0.49
     plataformas
    0.49
     কোম্পানি
    0.48
    𝚘
    0.47
     độc
    0.46
     જાય
    0.46
    影视
    0.46
    چھا
    0.46
     роль
    0.45
    Activations Density 0.001%

    No Known Activations