© 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. 14099
    Prev
    Next
    INDEX
    Explanations

    .dll files, locations, and specific terms

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

    Security Operations, Types, Salary, Vegetables, elastic

    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
    Pokud
    0.42
    Gosudarstvennyj
    0.40
    ཥ
    0.40
    если
    0.39
     puterea
    0.38
     CLIENTI
    0.38
    ErrorClazz
    0.38
    puede
    0.37
    Bechyné
    0.37
    Puede
    0.37
    POSITIVE LOGITS
    .
    0.61
    ,
    0.52
     Oceans
    0.45
    /
    0.44
     the
    0.43
     Amsterdam
    0.42
     or
    0.40
    0.40
     and
    0.40
     Minneapolis
    0.40
    Activations Density 0.036%

    No Known Activations