© 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. 122903
    Prev
    Next
    INDEX
    Explanations

    ultra low

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

    historical, intense, mysterious

    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
    যেমন
    0.50
    ১৯
    0.50
     ছন্দ
    0.49
    pexels
    0.48
    િલે
    0.47
    悅
    0.46
    ቮ
    0.46
    ᱵ
    0.46
     спорттук
    0.45
    貸
    0.45
    POSITIVE LOGITS
     Vás
    0.50
    ness
    0.48
     discretion
    0.46
     overboard
    0.45
     Stands
    0.45
     ____
    0.44
     podpis
    0.44
     ,
    0.43
     sacrific
    0.43
     ULTRA
    0.43
    Activations Density 0.001%

    No Known Activations