© 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. 160237
    Prev
    Next
    INDEX
    Explanations

    website, shields, applied, matched

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

    specific contexts and continuations

    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
    health
    0.48
    vVertex
    0.46
     Resultados
    0.46
    ridas
    0.45
    തായ
    0.45
     ojo
    0.44
    َى
    0.44
    tao
    0.44
    উদ্
    0.44
    Ŷ
    0.43
    POSITIVE LOGITS
    世界
    0.45
    階段
    0.45
    து
    0.43
    мпания
    0.43
    電機
    0.43
    لي
    0.42
    tering
    0.42
     عق
    0.41
    ังสือ
    0.40
    ሰው
    0.40
    Activations Density 0.001%

    No Known Activations