© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12689
    Prev
    Next
    INDEX
    Explanations

    dedication and acceleration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ịnh
    1.14
     vacun
    1.11
     procedimiento
    1.06
    トー
    1.06
     producto
    1.05
    錤
    1.03
    สู่
    1.01
     рее
    1.01
    ото
    1.00
     naka
    0.99
    POSITIVE LOGITS
     ८
    1.11
     Moż
    1.10
     Worse
    1.10
     crores
    1.10
    setInterval
    1.09
    ιλ
    1.09
     Ελλάδα
    1.09
    ੰਜਾਬ
    1.09
     μία
    1.07
    োয়
    1.07
    Activations Density 0.000%

    No Known Activations