© 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. 48651
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

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

    assume, authentic, launches

    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
     careless
    0.43
    狡
    0.42
     различные
    0.41
    某些
    0.40
     speciale
    0.40
     নূতন
    0.40
     chromat
    0.40
     perjury
    0.39
    roga
    0.39
    特殊的
    0.39
    POSITIVE LOGITS
     Traditionally
    0.45
    🥇
    0.43
     অথচ
    0.43
     sekaligus
    0.43
     Historically
    0.42
     然後
    0.42
     pię
    0.41
     そして
    0.41
    عاية
    0.40
     sambil
    0.40
    Activations Density 0.000%

    No Known Activations