© 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. 59289
    Prev
    Next
    INDEX
    Explanations

    any predicate, base64

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

    state of being or relation

    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
     USDT
    0.43
    在了
    0.42
     worries
    0.41
    リーナ
    0.41
    ảo
    0.40
     ডেলি
    0.40
    '$
    0.40
    摇头
    0.40
     '$
    0.40
    лл
    0.39
    POSITIVE LOGITS
     możesz
    0.44
     används
    0.44
     ergän
    0.43
     skapa
    0.42
     aanv
    0.41
    ដែលអាច
    0.41
    GIS
    0.41
     mogą
    0.41
     handeln
    0.40
     foragers
    0.39
    Activations Density 0.000%

    No Known Activations