© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5045
    Prev
    Next
    INDEX
    Explanations

    most important/critical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    Z
    0.64
    rete
    0.60
     upp
    0.57
    B
    0.56
    тения
    0.56
    Property
    0.55
     dor
    0.55
     રાશિ
    0.55
     Property
    0.55
     tez
    0.55
    POSITIVE LOGITS
    骗
    0.83
    Sorry
    0.76
     failed
    0.74
    騙
    0.73
     Sorry
    0.72
     Failed
    0.71
     invertible
    0.71
     Break
    0.70
     fools
    0.70
     Broken
    0.69
    Activations Density 0.110%

    No Known Activations