© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 11266
    Prev
    Next
    INDEX
    Explanations

    residence time distribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preference
    0.45
     multiplica
    0.42
    DATA
    0.41
    логи
    0.40
    메
    0.40
    Bloc
    0.39
    Cada
    0.39
     multitud
    0.39
    в
    0.39
    quin
    0.39
    POSITIVE LOGITS
     вступи
    0.47
     영향을
    0.45
     χρει
    0.43
    AVLNode
    0.43
    穵
    0.43
    ডিএফ
    0.42
     влияет
    0.42
    dbContext
    0.41
    影响力
    0.40
     здо
    0.40
    Activations Density 0.000%

    No Known Activations