© 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. 31-GEMMASCOPE-2-RES-65K
    4. 20338
    Prev
    Next
    INDEX
    Explanations

    word count for writing

    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
     X
    0.43
    TABLE
    0.42
     table
    0.39
     ved
    0.38
     andre
    0.38
     of
    0.37
     $
    0.37
     Whole
    0.37
     first
    0.37
    Table
    0.37
    POSITIVE LOGITS
    莯
    0.47
    ധ്യമ
    0.44
    ંમે
    0.44
    훈련
    0.42
    isième
    0.42
    तोड़
    0.41
    ্টিফি
    0.41
     ইস্যুতে
    0.40
    薹
    0.40
     تبدیلی
    0.39
    Activations Density 0.018%

    No Known Activations