© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14363
    Prev
    Next
    INDEX
    Explanations

    undefined constant followed by a name

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

    code, data, or measurements

    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_16k_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
    AYLOR
    0.37
     (
    0.36
     彼
    0.36
     सरस्व
    0.34
    pson
    0.33
    jej
    0.33
     jego
    0.33
     マン
    0.33
    他說
    0.33
    㝢
    0.33
    POSITIVE LOGITS
     kamera
    0.38
     memeriksa
    0.35
     gratu
    0.35
     logika
    0.35
    ۔
    0.34
     munka
    0.34
    மிருந்து
    0.33
     pesky
    0.33
     procédure
    0.33
     infraestructura
    0.33
    Activations Density 0.099%

    No Known Activations