© 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. 68495
    Prev
    Next
    INDEX
    Explanations

    locations and populations

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

    placesIt is part of

    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
     MgII
    0.46
    盜
    0.46
    農
    0.43
     আঙ্গ
    0.42
     ومت
    0.41
    豬
    0.41
     বিলম্ব
    0.41
    鴨
    0.41
    臘
    0.41
     rameaux
    0.41
    POSITIVE LOGITS
     believed
    0.48
    erious
    0.44
     famous
    0.43
    aving
    0.41
    iru
    0.41
    famous
    0.41
     stereotypical
    0.40
    퀴
    0.40
    ifstream
    0.39
    stere
    0.39
    Activations Density 0.002%

    No Known Activations