© 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. 6736
    Prev
    Next
    INDEX
    Explanations

    JSON formatting instructions

    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
     Spi
    0.63
    hig
    0.61
     Paragraph
    0.61
     bu
    0.61
     paragraphs
    0.60
     Prof
    0.60
    -,
    0.59
     ор
    0.58
     pap
    0.57
    orms
    0.57
    POSITIVE LOGITS
     Gosudarstvennyj
    0.79
     Reaktion
    0.76
     Addresses
    0.75
    сіі
    0.75
    ován
    0.75
     utilizan
    0.73
     সোমবার
    0.73
     በጥ
    0.73
    প্রায়
    0.73
    ൻ
    0.73
    Activations Density 0.036%

    No Known Activations