© 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. 11378
    Prev
    Next
    INDEX
    Explanations

    introducing, inde, echo, elevate, breach

    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
    sdag
    2.29
    써
    1.78
    cluding
    1.76
     TextEditing
    1.72
    cr
    1.69
    ssss
    1.66
    ના
    1.66
    cology
    1.64
    gning
    1.64
    Rit
    1.63
    POSITIVE LOGITS
    ်
    1.74
    ্শন
    1.73
    蔣
    1.72
     fillColor
    1.70
    बंदी
    1.62
     inequities
    1.62
    ື່ອ
    1.61
    і
    1.61
    ্সের
    1.60
     attaining
    1.60
    Activations Density 0.001%

    No Known Activations