© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4726
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges

    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
    Not in Any Lists

    No Comments

    Negative Logits
     зрения
    0.73
     Krim
    0.71
    Vers
    0.69
     flexible
    0.68
    Dem
    0.67
    ۰
    0.67
    Does
    0.66
     thirteen
    0.66
     Dem
    0.65
    ギ
    0.65
    POSITIVE LOGITS
     returning
    0.64
    ôme
    0.62
     कटो
    0.62
    xx
    0.62
     remaining
    0.60
    Poster
    0.60
    ністю
    0.59
    astă
    0.59
     monumento
    0.59
     return
    0.59
    Activations Density 0.221%

    No Known Activations