© 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. 2566
    Prev
    Next
    INDEX
    Explanations

    relative position or context

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

    other or inner

    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
    สำหรับ
    0.39
    ,--
    0.39
    ,~
    0.37
     کیفیت
    0.35
     kwaliteit
    0.35
     foncé
    0.35
     Orden
    0.34
     stesso
    0.34
    বারেই
    0.34
     Initialize
    0.34
    POSITIVE LOGITS
    ત્
    0.33
     blissful
    0.30
    ыска
    0.29
     cunt
    0.28
     inhabitants
    0.28
     meadows
    0.28
    ា
    0.28
     사람이
    0.28
     cocker
    0.27
    ﾄ
    0.27
    Activations Density 0.155%

    No Known Activations