© 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. 7406
    Prev
    Next
    INDEX
    Explanations

    notable achievements or items

    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
     of
    0.61
     của
    0.52
    新たに
    0.48
     della
    0.48
     way
    0.47
    োর
    0.47
    उ
    0.47
     are
    0.46
     you
    0.46
    industry
    0.46
    POSITIVE LOGITS
    喜欢的
    0.43
     גע
    0.40
     ресу
    0.40
     dilemmas
    0.39
     występ
    0.39
     связана
    0.39
     Horoscope
    0.38
    Potion
    0.38
     przyj
    0.37
    曰
    0.37
    Activations Density 0.059%

    No Known Activations