© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63551
    Prev
    Next
    INDEX
    Explanations

    VIP, who, city, love

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

    datetime parsing and system function

    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
    Negative Logits
    л
    0.50
    ру
    0.48
    illera
    0.48
    ገልግሎ
    0.44
    зяржа
    0.44
    schlag
    0.43
    壘
    0.43
     réaliser
    0.42
    延
    0.42
    끌
    0.42
    POSITIVE LOGITS
     CHILDREN
    0.52
     дети
    0.50
     Odysseus
    0.50
    
    0.50
     Penguin
    0.49
     PON
    0.48
     किड्स
    0.47
     Quiet
    0.47
    arlı
    0.47
     DEPENDENCIA
    0.47
    Activations Density 0.001%

    No Known Activations