© 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. 60807
    Prev
    Next
    INDEX
    Explanations

    which you / their expertise

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

    equations, numbers, and calculations

    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
     peculiar
    0.48
    LAT
    0.48
    浩
    0.45
    嗜
    0.45
    ем
    0.44
    ంశ
    0.43
    INFRINGEMENT
    0.43
    STEIN
    0.42
    してくれる
    0.42
    有望
    0.42
    POSITIVE LOGITS
     Mayıs
    0.52
     Kör
    0.51
     Bellev
    0.49
     archives
    0.48
     (
    0.47
     databases
    0.46
    desde
    0.45
     CNRS
    0.45
     Archives
    0.44
     Transition
    0.44
    Activations Density 0.000%

    No Known Activations