© 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-65K
    7. 36362
    Prev
    Next
    INDEX
    Explanations

    emerging research

    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_65k_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
    2
    0.48
    SSR
    0.47
    jel
    0.46
    eton
    0.46
    orb
    0.44
     Professions
    0.44
    1
    0.44
    िशन
    0.43
     PROFESSION
    0.43
     Militar
    0.43
    POSITIVE LOGITS
     assets
    0.47
     እንቅ
    0.46
     ود
    0.45
    作为
    0.43
     intakes
    0.43
     کوم
    0.43
     तरा
    0.43
    ك
    0.42
     או
    0.42
     éléments
    0.41
    Activations Density 0.009%

    No Known Activations