© 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. 7187
    Prev
    Next
    INDEX
    Explanations

    the most defining iconic must

    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
     右利き
    0.90
    🈂
    0.80
    wirkung
    0.80
    vant
    0.80
    🉑
    0.78
    љашње
    0.75
    🈯
    0.74
    🈚
    0.74
     ಪರಿ
    0.73
    latego
    0.72
    POSITIVE LOGITS
     بش
    1.16
     hologram
    1.13
     ك
    1.08
     idol
    1.07
     K
    1.07
     logout
    1.06
     (
    1.05
     weekly
    1.04
     comedic
    1.04
     emoji
    1.04
    Activations Density 0.208%

    No Known Activations