© 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. 132080
    Prev
    Next
    INDEX
    Explanations

    free sample

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

    role followed by description

    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
    NCE
    0.49
    ಕ್ಕಾಗಿ
    0.47
    决
    0.47
    촐
    0.46
    纭
    0.46
    総合
    0.45
     Preferably
    0.45
     tệ
    0.44
    讐
    0.43
    均为
    0.43
    POSITIVE LOGITS
     surrounding
    0.49
    or
    0.48
     bescherm
    0.48
    </h1>
    0.47
     elektry
    0.47
     when
    0.46
     ʻ
    0.46
    able
    0.46
     keď
    0.46
    cześ
    0.45
    Activations Density 0.004%

    No Known Activations