© 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. 111738
    Prev
    Next
    INDEX
    Explanations

    specific sequential phrases

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

    quote beginnings or phrases

    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
    প্রথম
    0.50
    Μ
    0.46
    iscuit
    0.45
    xn
    0.45
    ೀರ
    0.44
    的目的
    0.44
    ইসলাম
    0.43
     isomeric
    0.43
     Eye
    0.42
    лли
    0.42
    POSITIVE LOGITS
     tệ
    0.54
     أكثر
    0.50
     laranja
    0.50
     atualmente
    0.50
     systém
    0.49
     limite
    0.47
     į
    0.47
    ប៉
    0.47
    ě
    0.46
    ݨ
    0.46
    Activations Density 0.000%

    No Known Activations