© 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. 5314
    Prev
    Next
    INDEX
    Explanations

    describes attribute or role

    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
    Michigan
    0.58
    萃
    0.58
    Ke
    0.56
    bloom
    0.55
     Leeds
    0.55
     magneto
    0.54
    滢
    0.54
    Touches
    0.54
     bedding
    0.53
     blo
    0.53
    POSITIVE LOGITS
    達
    0.84
     equivalents
    0.83
    नीय
    0.83
    륭
    0.82
     समकक्ष
    0.82
     দাড়
    0.79
     중
    0.79
     கலோர
    0.78
    刑事
    0.78
     legislation
    0.78
    Activations Density 0.136%

    No Known Activations