© 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. 184185
    Prev
    Next
    INDEX
    Explanations

    this week

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

    foreign languages and 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
     contractual
    0.53
     судь
    0.52
     ساری
    0.46
     resolved
    0.45
    ⋄
    0.45
     mesmer
    0.45
     historical
    0.44
     termin
    0.44
     don
    0.43
     ночь
    0.43
    POSITIVE LOGITS
    ور
    0.53
    ötet
    0.52
    ம்தா
    0.50
    啄
    0.50
    要望
    0.49
    الك
    0.49
    撲
    0.49
     Großbritannien
    0.49
     Descripción
    0.48
    Twig
    0.48
    Activations Density 0.000%

    No Known Activations