© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 11336
    Prev
    Next
    INDEX
    Explanations

    links to articles or posts

    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
    nd
    0.75
    ్రీ
    0.62
    Policy
    0.61
     Policy
    0.60
    tection
    0.60
    型
    0.60
    สุด
    0.60
    $),
    0.59
    Return
    0.59
    izielle
    0.59
    POSITIVE LOGITS
     antice
    0.85
     भिखारी
    0.84
     stockbild
    0.79
     दास
    0.78
     esempl
    0.78
     sile
    0.78
     hoje
    0.76
     remarquer
    0.76
     crean
    0.75
     recreated
    0.75
    Activations Density 0.011%

    No Known Activations