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

    Neuronpedia

    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. 579
    Prev
    Next
    INDEX
    Explanations

    comparisons and surpassments

    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
     বসিয়া
    0.73
     उपयोगी
    0.73
    ท่อง
    0.69
     scheint
    0.68
     solutions
    0.67
     useful
    0.65
     полез
    0.64
    )):
    0.63
     literals
    0.63
    )));
    0.63
    POSITIVE LOGITS
    compared
    1.02
     compared
    1.00
     Compared
    0.95
     Compare
    0.95
    Compare
    0.94
     significantly
    0.90
     surpasses
    0.90
    比
    0.89
    Compared
    0.89
     surpassed
    0.88
    Activations Density 0.058%

    No Known Activations