© 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. 10718
    Prev
    Next
    INDEX
    Explanations

    starts with "Don" or "Don't"

    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
     sostiene
    2.55
    offsetWidth
    2.48
    题
    2.47
     concern
    2.46
    european
    2.45
    за
    2.43
    hips
    2.39
    dplyr
    2.38
    الم
    2.37
    ات
    2.35
    POSITIVE LOGITS
    derdag
    3.59
    ب
    3.11
    u
    3.00
    ৈতিক
    2.96
    swering
    2.94
     lysis
    2.90
    nées
    2.76
    त
    2.65
    nie
    2.65
    ality
    2.64
    Activations Density 0.099%

    No Known Activations