© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3202
    Prev
    Next
    INDEX
    Explanations

    math problems

    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_22_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
    Buildable
    0.71
     cuy
    0.69
    噠
    0.69
     जरी
    0.68
     registrant
    0.67
    стве
    0.67
    िडेट
    0.67
    voud
    0.66
    <unused14>
    0.66
    ternut
    0.66
    POSITIVE LOGITS
    What
    0.75
     What
    0.74
     মিথ্যা
    0.71
    ஆ
    0.70
    what
    0.70
     what
    0.69
    Question
    0.68
     Readings
    0.67
     Class
    0.67
     один
    0.66
    Activations Density 0.003%

    No Known Activations