© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 211708
    Prev
    Next
    INDEX
    Explanations

    moving and avoid dry

    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
    inplace
    0.41
    スム
    0.39
    pH
    0.39
     setUser
    0.38
    "!
    0.38
    ">${
    0.38
    vector
    0.37
     displace
    0.37
    (.*
    0.37
    "${
    0.37
    POSITIVE LOGITS
     چهار
    0.41
     Tudor
    0.39
     Noeud
    0.38
    跳
    0.38
     אור
    0.38
     Cinque
    0.37
     الدوري
    0.37
    undan
    0.37
     quadrado
    0.37
     时尚
    0.37
    Activations Density 0.003%

    No Known Activations