© 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. 132887
    Prev
    Next
    INDEX
    Explanations

    authentication device

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

    decisions made, who had, model [

    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
     যায়
    0.45
     graceful
    0.45
     soft
    0.44
     소프트
    0.44
    룔
    0.43
     gracefully
    0.42
     primarySwatch
    0.42
    ไหน
    0.41
     предметов
    0.40
    퀘
    0.40
    POSITIVE LOGITS
    ifier
    0.43
    ipple
    0.43
    ابقة
    0.41
    eram
    0.40
    eni
    0.39
    eno
    0.39
    ariam
    0.39
     Cone
    0.38
     организма
    0.38
    SM
    0.38
    Activations Density 0.000%

    No Known Activations