© 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. 2741
    Prev
    Next
    INDEX
    Explanations

    places and named entities

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

    brand and related context

    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
     భారతదేశ
    0.43
     ανθ
    0.42
    η
    0.42
    <unused2157>
    0.41
    <unused2019>
    0.40
     nx
    0.39
     σ
    0.39
    ährend
    0.39
     它
    0.38
     χρη
    0.38
    POSITIVE LOGITS
     الكبير
    0.47
    Leben
    0.46
    Че
    0.45
    اق
    0.44
     première
    0.43
    Casa
    0.43
     novedades
    0.42
     fatto
    0.40
    يان
    0.39
    Ха
    0.39
    Activations Density 0.211%

    No Known Activations