© 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. 40165
    Prev
    Next
    INDEX
    Explanations

    O King

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

    regular expression parsing

    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
    i
    0.52
     endemic
    0.50
     subcutaneous
    0.50
     apenas
    0.49
     causa
    0.48
     tipo
    0.47
     totalmente
    0.46
     brind
    0.46
     esiste
    0.46
     extensible
    0.46
    POSITIVE LOGITS
    ревнования
    0.49
     Joan
    0.47
    Joan
    0.46
    恽
    0.44
    Tanh
    0.43
    Abstraction
    0.43
    Came
    0.43
    Pause
    0.43
     নির্যাতন
    0.43
     Για
    0.42
    Activations Density 0.000%

    No Known Activations