© 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. 79993
    Prev
    Next
    INDEX
    Explanations

    sales, discounts, and items

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

    purpose, action, and consequence

    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
    传送
    0.48
    袅
    0.46
    wap
    0.44
     包括
    0.43
     كيفية
    0.43
    uities
    0.42
     لأ
    0.41
    告诉我
    0.41
     భాగ
    0.41
    ởi
    0.40
    POSITIVE LOGITS
     Z
    0.50
    BL
    0.45
    TL
    0.44
     mastering
    0.44
    FM
    0.44
     designing
    0.42
    designs
    0.42
     P
    0.42
    ES
    0.42
    QL
    0.42
    Activations Density 0.002%

    No Known Activations