© 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. 70361
    Prev
    Next
    INDEX
    Explanations

    rotating pan

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

    English, multi-language content

    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
     instruments
    0.48
     audacious
    0.47
    H
    0.47
     covenants
    0.47
    comps
    0.46
     thwart
    0.46
    O
    0.45
    "<<
    0.44
     文件
    0.44
     treatises
    0.44
    POSITIVE LOGITS
    及其
    0.54
    ধর্
    0.48
     অন্তর্
    0.47
    麺
    0.47
    arks
    0.46
    搅拌
    0.46
     અને
    0.46
     에너지
    0.46
    wash
    0.45
     ਅਤੇ
    0.45
    Activations Density 0.001%

    No Known Activations