© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11596
    Prev
    Next
    INDEX
    Explanations

    dependency parsing and management

    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
    ık
    2.83
    事物
    2.75
    во
    2.72
    ik
    2.61
     तरह
    2.61
    antial
    2.60
    、​
    2.60
    вости
    2.58
     fizer
    2.56
    ュ
    2.54
    POSITIVE LOGITS
     twos
    3.47
    ことなく
    2.88
     Vicki
    2.78
     Nervous
    2.76
    startIndex
    2.74
    री
    2.70
    erent
    2.68
     honestly
    2.65
    Vanessa
    2.62
    WebElement
    2.61
    Activations Density 0.066%

    No Known Activations