© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5300
    Prev
    Next
    INDEX
    Explanations

    date and schedule

    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_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     (
    1.40
     It
    1.29
     The
    1.24
    .
    1.16
     or
    1.15
     How
    1.09
     and
    1.05
     If
    1.01
    1.01
     There
    1.01
    POSITIVE LOGITS
    𒆉
    1.29
    𒈣
    1.28
    𒈖
    1.28
    𒂀
    1.28
    𒈻
    1.27
    𒍗
    1.27
    𒆦
    1.27
    𒂁
    1.27
    𒌚
    1.27
    𒀑
    1.27
    Activations Density 0.000%

    No Known Activations