© 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. 11934
    Prev
    Next
    INDEX
    Explanations

    numbers in dates and times

    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
    -
    0.71
    PC
    0.60
     overhead
    0.60
    regarding
    0.58
     中
    0.57
    SH
    0.57
    posed
    0.57
    ভিত্তিক
    0.57
     January
    0.57
    Rights
    0.55
    POSITIVE LOGITS
     hInstance
    0.95
     Tutto
    0.92
     İl
    0.86
    <unused994>
    0.86
    苚
    0.84
    <unused1810>
    0.82
    স্থাপ
    0.82
     Tudo
    0.82
     фай
    0.82
     ;\
    0.82
    Activations Density 0.016%

    No Known Activations