© 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. 54556
    Prev
    Next
    INDEX
    Explanations

    answering your questions

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

    analyzing and understanding trends

    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
    न्नई
    0.57
    GTUIKit
    0.52
     ሆ
    0.52
     বিভ
    0.52
     요거
    0.52
    でしたが
    0.50
    이었다
    0.50
    之际
    0.50
     ngunit
    0.50
    ydı
    0.49
    POSITIVE LOGITS
    k
    0.51
     Januari
    0.50
    d
    0.47
     I
    0.46
     thrown
    0.46
     Liberals
    0.44
    January
    0.42
     o
    0.41
     L
    0.40
     LEFT
    0.40
    Activations Density 0.000%

    No Known Activations