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. 9-GEMMASCOPE-2-RES-262K
    4. 7485
    Prev
    Next
    INDEX
    Explanations

    variable references and declarations

    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_9_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
    ளைஞ
    2.14
     जहरी
    2.00
     tensors
    1.98
     enthalpy
    1.97
    න්
    1.95
     ∣
    1.94
     artillery
    1.94
     aaye
    1.89
    itchfield
    1.87
    jmath
    1.87
    POSITIVE LOGITS
    ه
    2.78
     dotycz
    2.28
    मर्श
    1.97
    o
    1.96
    ことです
    1.96
    ી
    1.92
    ことになる
    1.91
    bit
    1.90
    ം
    1.90
    i
    1.89
    Activations Density 0.130%

    No Known Activations