Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1542
    Prev
    Next
    INDEX
    Explanations

    words starting with Po, Lo, Go, Ro, Bo

    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
    ぁ
    0.78
    m
    0.76
     priorit
    0.74
     priority
    0.74
    นาน
    0.74
    ところ
    0.73
    िका
    0.72
    률
    0.71
    ಯಲ್ಲಿ
    0.71
    น้อย
    0.71
    POSITIVE LOGITS
    fficial
    1.73
    pportunities
    1.70
    pportun
    1.67
    pped
    1.63
    ğlu
    1.42
    ffic
    1.40
    pping
    1.35
    ctrine
    1.32
    oooo
    1.31
    pper
    1.30
    Activations Density 0.562%

    No Known Activations