© 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. 14022
    Prev
    Next
    INDEX
    Explanations

    concise phrasing and word choice

    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
     refiere
    0.35
     写
    0.34
     acabó
    0.34
    bauen
    0.34
    apabb
    0.33
     escreveu
    0.33
     页
    0.32
    urètre
    0.32
    avacanam
    0.31
    苋
    0.31
    POSITIVE LOGITS
    /
    0.44
    -
    0.34
     (
    0.29
     vending
    0.29
    開催
    0.29
    ,
    0.29
     garantire
    0.28
    ℠
    0.27
    럭
    0.27
     opportunities
    0.27
    Activations Density 0.104%

    No Known Activations