© 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-16K
    7. 3286
    Prev
    Next
    INDEX
    Explanations

    the trevor project

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     paise
    0.98
    iseconds
    0.95
     ст
    0.95
     Ode
    0.93
     Byst
    0.93
     Eats
    0.91
     TBA
    0.90
     Tidal
    0.88
     Combin
    0.88
    ᅲ
    0.88
    POSITIVE LOGITS
    mselves
    1.63
    oretically
    1.57
    jenigen
    1.46
    atrical
    1.43
    atre
    1.34
    matic
    1.33
    ophylline
    1.25
    orems
    1.23
    oretical
    1.23
    orical
    1.22
    Activations Density 0.207%

    No Known Activations