© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 99549
    Prev
    Next
    INDEX
    Explanations

    purchase and add to cart

    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
    getTag
    0.46
     fadeIn
    0.45
     Giov
    0.45
     nuova
    0.42
    Giov
    0.41
     tagging
    0.40
     Geographical
    0.40
    桢
    0.39
     Fresh
    0.39
    旪
    0.39
    POSITIVE LOGITS
     revenue
    0.48
     departed
    0.45
     contentType
    0.43
     abandoned
    0.41
    cargo
    0.40
    contentType
    0.40
    newsletter
    0.40
    emp
    0.39
    coupon
    0.39
    conten
    0.39
    Activations Density 0.009%

    No Known Activations