© 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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 5297
    Prev
    Next
    INDEX
    Explanations

    time periods and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     Quelques
    0.84
    開始
    0.73
    섰
    0.73
    Inicio
    0.72
     mấy
    0.71
    ucin
    0.70
    ೪
    0.70
     시작
    0.68
    几天
    0.68
    遺跡
    0.68
    POSITIVE LOGITS
     full
    0.84
     calendar
    0.77
     permissible
    0.69
     unlimited
    0.68
     affirmative
    0.66
     properly
    0.66
     calendars
    0.66
     business
    0.65
     standard
    0.65
     valid
    0.64
    Activations Density 0.087%

    No Known Activations