© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6827
    Prev
    Next
    INDEX
    Explanations

    Sp followed by completions

    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
    Negative Logits
    omon
    0.72
    폼
    0.66
     police
    0.65
     Link
    0.58
     Pad
    0.58
    Link
    0.57
    creto
    0.57
    assigned
    0.56
     मॉल
    0.54
     nervous
    0.54
    POSITIVE LOGITS
     resa
    0.68
     hearsay
    0.67
    тності
    0.65
    timeLeft
    0.63
    吽
    0.62
     parses
    0.62
     किम
    0.61
     ayudan
    0.61
     comulti
    0.61
     dél
    0.61
    Activations Density 0.070%

    No Known Activations