© 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. 163797
    Prev
    Next
    INDEX
    Explanations

    service or requirement

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

    new service or product names

    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
    functions
    0.52
     займа
    0.49
    К
    0.47
    🍐
    0.46
    executionContext
    0.45
    🥄
    0.45
    ром
    0.44
     périodes
    0.44
    ԝ
    0.44
    🙎
    0.43
    POSITIVE LOGITS
     सेवा
    0.55
    brella
    0.52
     Polaris
    0.50
     service
    0.50
     Victoria
    0.49
     Nova
    0.49
    ure
    0.48
     OM
    0.48
     nova
    0.48
     OMS
    0.47
    Activations Density 0.000%

    No Known Activations