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. 981
    Prev
    Next
    INDEX
    Explanations

    HTML body content

    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
    <unused40>
    0.99
    瑷
    0.88
    انوں
    0.88
    <unused28>
    0.82
     ଆ
    0.82
    <unused53>
    0.82
     சேவை
    0.82
    виа
    0.81
     Enseñanza
    0.80
    <unused26>
    0.80
    POSITIVE LOGITS
    <body>
    1.93
     body
    1.49
    body
    1.38
     Body
    1.31
     bodies
    1.25
    </html>
    1.23
    Body
    1.21
    बॉडी
    1.14
    身体
    1.10
    <html>
    1.10
    Activations Density 0.045%

    No Known Activations