© 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. 1579
    Prev
    Next
    INDEX
    Explanations

    types of language use

    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
    нология
    0.31
    蛲
    0.29
    волю
    0.28
     параметр
    0.28
    ]，
    0.27
     шрифт
    0.27
    瞍
    0.27
    ！！！
    0.26
    денти
    0.26
     Executor
    0.26
    POSITIVE LOGITS
    ies
    0.29
    lain
    0.28
    li
    0.28
    long
    0.27
    lv
    0.27
    land
    0.26
    lng
    0.26
    lou
    0.26
    lom
    0.26
    time
    0.25
    Activations Density 0.000%

    No Known Activations