© 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. 228727
    Prev
    Next
    INDEX
    Explanations

    foreign language 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
     를
    0.48
    Coref
    0.46
     если
    0.45
     √(
    0.45
    🔒
    0.44
     என்கிறார்
    0.44
    ×
    0.43
    ԁ
    0.42
    xg
    0.42
     Ω
    0.42
    POSITIVE LOGITS
     République
    0.50
     continuidad
    0.48
     لمدة
    0.46
    ਿੰ
    0.45
    飪
    0.45
     alla
    0.45
     bereits
    0.44
    mer
    0.44
    ômes
    0.44
     vergangenen
    0.43
    Activations Density 0.001%

    No Known Activations