© 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. 10984
    Prev
    Next
    INDEX
    Explanations

    rinsing and draining thoroughly

    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
    াধ্য
    0.72
    ด้อ
    0.65
    iaxial
    0.65
    ังก์ชัน
    0.61
    (/(
    0.60
    phol
    0.59
    otika
    0.58
    perti
    0.57
     தனிநாயகம்
    0.57
    ሯ
    0.57
    POSITIVE LOGITS
     excess
    0.79
     off
    0.76
     exceso
    0.75
    试验
    0.73
     out
    0.72
     suivre
    0.70
     exces
    0.70
     purged
    0.69
     extraneous
    0.67
     voie
    0.66
    Activations Density 0.028%

    No Known Activations