© 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. 203705
    Prev
    Next
    INDEX
    Explanations

    listing or introducing

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

    reading Chinese

    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
     بیوی
    0.47
    ките
    0.46
    ethylamine
    0.46
    香味
    0.46
    妇
    0.44
    펨
    0.43
     تشخیص
    0.43
    에
    0.43
    쥬
    0.43
    资
    0.43
    POSITIVE LOGITS
    wirk
    0.46
     Sociales
    0.46
    Painting
    0.44
    Carta
    0.44
    Social
    0.43
     त्य
    0.42
    Fiction
    0.42
     spielen
    0.41
     suerte
    0.41
     Croatian
    0.41
    Activations Density 0.000%

    No Known Activations