© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9752
    Prev
    Next
    INDEX
    Explanations

    output ( or →

    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
    arbeiten
    1.45
     corpora
    1.31
     outfielder
    1.26
     }-\
    1.21
    ことを
    1.18
    layoutWidget
    1.18
     seo
    1.17
     urg
    1.16
    ⺌
    1.15
     bản
    1.15
    POSITIVE LOGITS
    ์
    1.36
    러
    1.22
    oretical
    1.19
    ️
    1.19
    례
    1.19
    ity
    1.18
    ist
    1.17
     fittest
    1.14
     Legendary
    1.13
     Ethical
    1.13
    Activations Density 0.000%

    No Known Activations