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. 9-GEMMASCOPE-2-RES-262K
    4. 7362
    Prev
    Next
    INDEX
    Explanations

    code, programming, system

    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
     ocor
    1.06
     conducir
    0.94
     wäre
    0.94
     küm
    0.86
    $("
    0.86
     kontinu
    0.86
    ្ស
    0.85
    $('
    0.84
     chết
    0.83
     '';
    0.83
    POSITIVE LOGITS
    an
    1.33
    oretically
    1.21
     Adele
    1.15
    theless
    1.12
    обходимо
    1.12
    скольку
    1.03
    gripper
    1.03
    रुख
    1.03
    in
    1.02
    anese
    1.02
    Activations Density 0.161%

    No Known Activations