© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 10626
    Prev
    Next
    INDEX
    Explanations

    value after comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ל
    1.42
    л
    1.22
    א
    1.22
    ล
    1.15
    า
    1.13
    ف
    1.13
    ло
    1.09
    지도
    1.09
    ק
    1.09
     karenge
    1.05
    POSITIVE LOGITS
    なかった
    1.23
     entrants
    1.20
     agrupación
    1.20
     tanaman
    1.16
     panahon
    1.14
     ujian
    1.13
     instrucciones
    1.13
     travellers
    1.12
    PathVariable
    1.11
     contestants
    1.11
    Activations Density 0.111%

    No Known Activations