© 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. 164511
    Prev
    Next
    INDEX
    Explanations

    variety of designs

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

    supplementing other methods

    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
    일까지
    0.48
     opulent
    0.46
     antes
    0.44
     पैसों
    0.44
     devenue
    0.43
    weekday
    0.43
     चौथे
    0.43
     ഊ
    0.42
    ahaha
    0.42
    三天
    0.42
    POSITIVE LOGITS
    Rotatef
    0.51
     असमान
    0.46
     রাজ্য
    0.45
    Languages
    0.45
     labelled
    0.44
    常见的
    0.44
     refined
    0.44
    ，
    0.44
     filesystem
    0.43
     রেজ
    0.43
    Activations Density 0.002%

    No Known Activations