© 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. 5722
    Prev
    Next
    INDEX
    Explanations

    because he was outstanding

    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
     variant
    0.75
     Called
    0.64
     metamorphosis
    0.64
    ]`
    0.62
    iegel
    0.61
     called
    0.60
     taps
    0.60
     variants
    0.56
     cốc
    0.56
     named
    0.56
    POSITIVE LOGITS
    嶆
    0.82
    完善
    0.81
     GridPane
    0.80
    初始化
    0.74
    Respiratory
    0.74
    तृ
    0.74
     종합
    0.74
     初始化
    0.73
     Keine
    0.72
     підтрим
    0.72
    Activations Density 0.016%

    No Known Activations