© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5231
    Prev
    Next
    INDEX
    Explanations

    code control flow

    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
     বিমানবন্দ
    0.70
    ...',
    0.69
    `,
    0.68
    ",
    0.67
    olab
    0.67
    .",
    0.67
    ...",
    0.67
    SAR
    0.66
    is
    0.66
    imy
    0.66
    POSITIVE LOGITS
     Else
    0.75
    ("|"+"
    0.72
    ваць
    0.68
    ↵↵↵↵↵↵↵↵↵↵
    0.67
     else
    0.66
    ↵↵↵↵↵↵↵↵
    0.66
     rbind
    0.64
     cheerio
    0.63
     mailed
    0.61
     indented
    0.61
    Activations Density 0.070%

    No Known Activations