© 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. 123205
    Prev
    Next
    INDEX
    Explanations

    terms in regulations

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

    punctuation and foreign phrases

    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
    t
    0.64
    p
    0.52
    त
    0.51
    ن
    0.51
    ক
    0.50
     an
    0.50
    लं
    0.46
    y
    0.46
    پ
    0.46
    o
    0.45
    POSITIVE LOGITS
     ብዙ
    0.53
    delen
    0.53
     Prozess
    0.52
     Direkt
    0.51
     রপ্ত
    0.51
     चाहती
    0.50
    他に
    0.50
    ností
    0.50
     Gandhiji
    0.50
     Regeln
    0.49
    Activations Density 0.000%

    No Known Activations