© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12185
    Prev
    Next
    INDEX
    Explanations

    numerical dosages and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lige
    1.28
    ,}$
    1.18
    cdot
    1.12
    bilical
    1.11
    yscy
    1.09
     ELF
    1.09
     oligos
    1.08
     flint
    1.08
    tutorials
    1.08
    d
    1.07
    POSITIVE LOGITS
    ع
    1.69
    же
    1.55
    та
    1.46
    ша
    1.44
    о
    1.43
    ин
    1.39
    Tama
    1.35
     бывает
    1.35
     Тя
    1.35
    съ
    1.34
    Activations Density 0.002%

    No Known Activations