© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144981
    Prev
    Next
    INDEX
    Explanations

    Cava-Chin vomiting

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

    however, exceptions, contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    asjon
    0.47
    ാ
    0.45
    cussion
    0.45
    ା
    0.45
    会議
    0.44
    重要な
    0.44
    ሌ
    0.44
    バッグ
    0.43
    駕
    0.43
    ope
    0.43
    POSITIVE LOGITS
     dị
    0.49
     ????
    0.48
     技术
    0.48
     அதிசய
    0.48
     du
    0.47
     Hyper
    0.47
     eerie
    0.47
     지나
    0.46
     Hot
    0.46
    渺
    0.46
    Activations Density 0.000%

    No Known Activations