© 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. 25504
    Prev
    Next
    INDEX
    Explanations

    electrical systems

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

    specific details or descriptions

    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
    ват
    0.44
    fundamental
    0.43
    RequestBuilder
    0.43
     разби
    0.42
    深圳
    0.42
    CP
    0.42
    funded
    0.41
    램
    0.41
    AssetsRequest
    0.41
    CHS
    0.41
    POSITIVE LOGITS
    を使
    0.51
     technologie
    0.51
     membrana
    0.51
     Audience
    0.49
     imped
    0.49
     grille
    0.49
     umožňuje
    0.48
    ⵕ
    0.48
     incarceration
    0.48
     الكهربائيه
    0.47
    Activations Density 0.000%

    No Known Activations