© 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. 86028
    Prev
    Next
    INDEX
    Explanations

    foreign characters and terms

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

    generous donation, quick fix, web interface

    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
     Bulg
    0.47
    梔
    0.46
     Bru
    0.46
     pergunt
    0.46
    莪
    0.45
    Acet
    0.45
    исто
    0.45
     owed
    0.44
    誣
    0.44
     FileWriter
    0.44
    POSITIVE LOGITS
    beel
    0.46
     نئی
    0.43
    line
    0.43
    fence
    0.43
     തുടങ്ങ
    0.43
     необхідно
    0.42
     новий
    0.42
    anz
    0.41
     นับ
    0.41
    🚴
    0.41
    Activations Density 0.001%

    No Known Activations