© 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. 10748
    Prev
    Next
    INDEX
    Explanations

    run followed by state or action

    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
    Negative Logits
    𝓂
    1.12
    ма
    1.08
    }");
    1.07
    '>";
    1.07
     eixo
    1.06
    البه
    1.05
     tars
    1.04
    𝓈
    1.03
    ία
    1.03
    ਰੇ
    1.03
    POSITIVE LOGITS
     errands
    2.25
    nin
    1.74
     smoothly
    1.64
    aways
    1.47
    nung
    1.44
     advertisements
    1.37
    nings
    1.36
    tests
    1.34
    nym
    1.34
    abouts
    1.33
    Activations Density 0.056%

    No Known Activations