© 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. 31-GEMMASCOPE-2-RES-262K
    7. 71138
    Prev
    Next
    INDEX
    Explanations

    although potentially

    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_31_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
    Lil
    0.48
    Pip
    0.44
     nalazi
    0.41
    \
    0.41
    _{*
    0.41
     dine
    0.41
    𝙇
    0.40
    _{\
    0.40
    ikaze
    0.40
     لكن
    0.39
    POSITIVE LOGITS
     árabe
    0.46
     refinements
    0.45
    ණ්ඩ
    0.44
     unnecessarily
    0.43
     anxieties
    0.43
    кович
    0.43
     circuitry
    0.43
     tradeoffs
    0.42
     برگ
    0.42
     aficionados
    0.42
    Activations Density 0.005%

    No Known Activations