© 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. 135529
    Prev
    Next
    INDEX
    Explanations

    Foreign languages and punctuation

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

    rich past

    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
    kmale
    0.45
    bine
    0.44
     १८४
    0.44
    biet
    0.44
    etric
    0.43
    ೬
    0.43
    ba
    0.42
    enix
    0.42
    ansa
    0.42
    odon
    0.42
    POSITIVE LOGITS
    教育
    0.47
     mög
    0.47
    看
    0.47
    长
    0.47
    惮
    0.47
    ری
    0.46
    点击
    0.46
     tijd
    0.45
     Samen
    0.45
    ুক
    0.45
    Activations Density 0.001%

    No Known Activations