© 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. 156070
    Prev
    Next
    INDEX
    Explanations

    foreign languages / scripts

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

    listing structure

    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
    ⁣⁣
    0.50
     使っ
    0.49
     Taman
    0.47
     cór
    0.46
     dolar
    0.45
    bamos
    0.44
     फैक्टर
    0.42
     Mallorca
    0.42
     രണ്ട്
    0.42
     અમારી
    0.42
    POSITIVE LOGITS
    arang
    0.39
     ولكن
    0.39
     peintre
    0.39
    纭
    0.39
     onerror
    0.38
    鹤
    0.38
     фаразлау
    0.38
    藝
    0.38
     профессиона
    0.37
    がありますが
    0.37
    Activations Density 0.001%

    No Known Activations