© 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. 134057
    Prev
    Next
    INDEX
    Explanations

    non-latin characters or phonetic representations

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

    rules, not trace

    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
     disposizione
    0.51
     dispoz
    0.50
     suces
    0.49
    檎
    0.48
     ಹೊಂದಿದೆ
    0.48
     pérdida
    0.47
    дит
    0.47
     dispuesto
    0.47
    UM
    0.47
    είου
    0.46
    POSITIVE LOGITS
    ল
    0.49
    res
    0.48
    로
    0.48
    ص
    0.47
    ko
    0.45
    ש
    0.45
    tz
    0.45
    tte
    0.45
    ج
    0.44
    in
    0.43
    Activations Density 0.001%

    No Known Activations