© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3125
    Prev
    Next
    INDEX
    Explanations

    irritable bowel syndrome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    퍁
    2.75
     strListName
    2.71
    𒆗
    2.71
    𒄯
    2.70
     nCharString
    2.70
     spacerItem
    2.69
     "{!}
    2.69
    ꗭ
    2.68
     trataro
    2.67
    𒁾
    2.66
    POSITIVE LOGITS
    ne
    1.95
    of
    1.83
    0
    1.77
    1
    1.71
    3
    1.70
    T
    1.70
    4
    1.66
    5
    1.60
    9
    1.59
    _
    1.57
    Activations Density 0.033%

    No Known Activations