© 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. 219000
    Prev
    Next
    INDEX
    Explanations

    foreign languages and financial/descriptive terms

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

    sequences of specific words

    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
    着
    0.50
    当
    0.47
    意見
    0.46
    一起
    0.46
    当作
    0.45
    Авто
    0.43
    第一次
    0.42
    釐
    0.42
    作用
    0.41
    رمی
    0.41
    POSITIVE LOGITS
     modelos
    0.52
     hohen
    0.52
     hohe
    0.50
     françaises
    0.50
     modellen
    0.50
     düşük
    0.49
     Cô
    0.47
     erreicht
    0.47
     Aşağı
    0.47
     matchup
    0.47
    Activations Density 0.000%

    No Known Activations