© 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-65K
    7. 8892
    Prev
    Next
    INDEX
    Explanations

    UI components and layout

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     scant
    0.86
     trouxe
    0.86
     imitating
    0.85
     pask
    0.80
     screamed
    0.79
     there
    0.79
     psychology
    0.78
     setTitle
    0.78
    <unused1953>
    0.77
    
    0.77
    POSITIVE LOGITS
    rası
    0.98
    Pic
    0.95
    Dimension
    0.90
    pic
    0.83
    Raw
    0.83
    Variety
    0.82
    sas
    0.82
    Flat
    0.81
    A
    0.81
    tall
    0.81
    Activations Density 0.010%

    No Known Activations