© 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. 237367
    Prev
    Next
    INDEX
    Explanations

    royal canadian mint

    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
    ⓒ
    0.49
     конец
    0.49
     карка
    0.49
    기업
    0.48
     catast
    0.47
     nike
    0.47
    𝔀
    0.46
    צת
    0.45
     AMOLED
    0.45
    .³
    0.45
    POSITIVE LOGITS
     മറ്റ
    0.48
     Département
    0.47
    Dept
    0.45
    锰
    0.45
     which
    0.44
     that
    0.43
    অন্য
    0.43
    灵
    0.42
    spectral
    0.42
    <0x91>
    0.41
    Activations Density 0.000%

    No Known Activations