© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13506
    Prev
    Next
    INDEX
    Explanations

    abdomen and ischemia

    np_acts-logits-general · gemini-2.5-flash-lite

    references to the abdomen and related anatomical regions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mehrm
    -2.64
    葙
    -2.58
    and
    -2.53
    Similarly
    -2.19
     sämtliche
    -2.19
    _
    -2.13
     mehrfach
    -2.11
    Likewise
    -2.09
    %
    -2.06
     Jugendliche
    -2.05
    POSITIVE LOGITS
    狁
    2.84
     utilisons
    2.72
    哢
    2.50
    tienen
    2.47
    鹟
    2.45
    ⢊
    2.45
    zelfde
    2.36
    uiente
    2.28
    疍
    2.25
    兕
    2.22
    Activations Density 0.005%

    No Known Activations