© 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. 88022
    Prev
    Next
    INDEX
    Explanations

    research questions

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

    documentation process

    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
     پیسے
    0.55
    嘘
    0.52
    Cheap
    0.47
     Cheap
    0.47
    ラス
    0.46
    負
    0.45
     पैसे
    0.44
    な
    0.44
    諺
    0.44
    тери
    0.43
    POSITIVE LOGITS
     ім
    0.53
     ù
    0.50
     preparación
    0.50
     canaliculato
    0.49
     开始
    0.48
     preparazione
    0.48
     effortlessly
    0.47
     eléct
    0.47
     célula
    0.46
     épu
    0.46
    Activations Density 0.001%

    No Known Activations