© 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. 22-GEMMASCOPE-2-RES-262K
    7. 10955
    Prev
    Next
    INDEX
    Explanations

    bott, bottle, bot contexts

    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_22_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
    ва
    1.45
     driveway
    1.14
     câ
    1.13
     dtype
    1.11
    dominant
    1.05
    ോ
    1.05
     countertop
    1.03
    возмо
    1.02
     بسيطه
    1.02
     reputation
    1.01
    POSITIVE LOGITS
    ique
    1.25
    elhos
    1.25
    scotch
    1.19
     целях
    1.19
     atte
    1.15
    ignore
    1.14
    丁
    1.13
    IQUE
    1.13
    ICAS
    1.11
    iques
    1.11
    Activations Density 0.058%

    No Known Activations