© 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. 244718
    Prev
    Next
    INDEX
    Explanations

    p-values

    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
     dort
    0.46
    ೮
    0.45
     によ
    0.43
     hypothalamic
    0.42
     学
    0.41
     பாராட்ட
    0.40
    ⱼ
    0.40
    ENTAL
    0.40
    韋
    0.40
    Font
    0.40
    POSITIVE LOGITS
     upto
    0.49
     автори
    0.45
    ға
    0.45
    вис
    0.45
    ът
    0.43
    UpDown
    0.43
    वेल
    0.43
     ভ্র
    0.42
    ған
    0.42
    лки
    0.41
    Activations Density 0.001%

    No Known Activations