© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 59984
    Prev
    Next
    INDEX
    Explanations

    exhibitions and installations

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

    current options, thousands, management

    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
    졀
    0.48
    sss
    0.47
    यिक
    0.47
    すすめ
    0.47
    гер
    0.47
     तपास
    0.46
    伝統
    0.46
     direto
    0.46
    бно
    0.46
    }^{-}
    0.45
    POSITIVE LOGITS
     booths
    0.52
     keys
    0.45
     installation
    0.44
     Eighteenth
    0.44
    %
    0.44
     inaugural
    0.43
     прибыли
    0.43
     Exhibition
    0.42
     Installation
    0.42
     exhibitions
    0.42
    Activations Density 0.000%

    No Known Activations