© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5961
    Prev
    Next
    INDEX
    Explanations

    parameter types and defaults

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     wards
    0.74
    supreme
    0.72
    Quit
    0.69
     Bedrooms
    0.68
    <0xDC>
    0.67
     Clark
    0.67
    overhead
    0.66
     CPU
    0.65
     Bonner
    0.65
    ches
    0.64
    POSITIVE LOGITS
     तालि
    0.66
     जागर
    0.65
    મત
    0.64
    媒
    0.63
     ranging
    0.63
     ফ্যা
    0.62
     umož
    0.60
    default
    0.60
    ǜ
    0.60
    ቻ
    0.59
    Activations Density 0.384%

    No Known Activations