© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 406
    Prev
    Next
    INDEX
    Explanations

    tasks, topics, and sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    ď
    1.57
    姊
    1.48
    puts
    1.45
    down
    1.41
    pero
    1.39
    di
    1.32
    ペーン
    1.31
    adă
    1.30
    ementia
    1.30
     drills
    1.29
    POSITIVE LOGITS
    abhut
    2.08
    rinsic
    2.01
    totalSupply
    1.81
     tê
    1.77
     ambient
    1.73
    椙
    1.71
     транспорт
    1.68
    ANCEL
    1.68
    птовалю
    1.68
     autonome
    1.66
    Activations Density 0.025%

    No Known Activations