© 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. 9206
    Prev
    Next
    INDEX
    Explanations

    there are numbers

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

    look around you

    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
     entice
    0.61
    ombasa
    0.48
     gateways
    0.46
     respond
    0.46
     ಲ
    0.46
    ambique
    0.46
     poumon
    0.46
    ucapkan
    0.45
    䢙
    0.45
     indonesia
    0.45
    POSITIVE LOGITS
    س
    0.54
    ס
    0.53
    امد
    0.52
    电脑
    0.49
    摄影
    0.48
     बिग
    0.44
     düz
    0.43
    পরিস
    0.43
    庚
    0.43
    逻辑
    0.42
    Activations Density 0.000%

    No Known Activations