© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4010
    Prev
    Next
    INDEX
    Explanations

    wide variation

    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_29_width_65k_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
    ጠቀም
    0.73
    靕
    0.72
    મિક
    0.66
    criptor
    0.66
    orsk
    0.64
    ディオ
    0.63
    椹
    0.63
    క్సి
    0.63
    斦
    0.62
    কেলে
    0.61
    POSITIVE LOGITS
     wide
    4.72
     broad
    4.56
     wider
    4.24
     Wide
    4.19
     widen
    4.16
     width
    4.15
    Wide
    4.09
     widened
    4.02
     широ
    3.95
     Broad
    3.93
    Activations Density 0.917%

    No Known Activations