© 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. 6605
    Prev
    Next
    INDEX
    Explanations

    result of 6

    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
     শ
    0.72
     Гон
    0.71
    лоба
    0.70
    मै
    0.70
     रामकृष्ण
    0.70
     cag
    0.70
    વિ
    0.70
     eri
    0.69
    ámico
    0.69
     കണ്ണ
    0.69
    POSITIVE LOGITS
     shot
    0.70
    ే
    0.64
     shots
    0.60
    ことです
    0.60
    inus
    0.59
     hinaus
    0.58
     gereken
    0.58
     tat
    0.57
     geno
    0.57
     proper
    0.57
    Activations Density 0.051%

    No Known Activations