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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 900
    Prev
    Next
    INDEX
    Explanations

    examples or lists

    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_262k_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
    :
    0.96
    (
    0.90
    :
    0.73
    "
    0.70
    Remark
    0.68
    '
    0.66
    ...
    0.65
    ,
    0.64
    All
    0.63
    -
    0.63
    POSITIVE LOGITS
     etc
    1.46
     그리고
    1.07
     illetve
    1.05
    以及
    1.02
    そして
    1.00
     especially
    0.98
    etc
    0.98
     odnosno
    0.98
     including
    0.94
     valamint
    0.92
    Activations Density 1.131%

    No Known Activations