© 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. 199877
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    explaining concepts with diverse examples

    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
    Hid
    0.48
    Fit
    0.46
    合格
    0.45
    A
    0.43
    HID
    0.43
    バ
    0.43
     serializer
    0.42
    C
    0.42
    EF
    0.42
    CSS
    0.42
    POSITIVE LOGITS
     зеле
    0.47
    ούν
    0.47
    гова
    0.46
     судо
    0.46
     partant
    0.46
    ❯
    0.46
     জীবন
    0.45
    rät
    0.45
     rozwiązania
    0.45
     живота
    0.45
    Activations Density 0.000%

    No Known Activations