© 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. 14809
    Prev
    Next
    INDEX
    Explanations

    combination of digits

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

    phrases indicating transition or questions

    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
     följande
    0.55
     hưởng
    0.54
    。</
    0.53
     getMax
    0.52
     následuj
    0.52
     ká
    0.52
     kar
    0.51
     模型
    0.51
     tặng
    0.51
     നാല
    0.51
    POSITIVE LOGITS
    M
    0.58
    s
    0.55
    T
    0.54
    t
    0.53
    т
    0.50
    U
    0.49
    chrome
    0.49
    )
    0.48
    riot
    0.48
    L
    0.47
    Activations Density 0.000%

    No Known Activations