© 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. 183000
    Prev
    Next
    INDEX
    Explanations

    coarse silt product

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

    human body, voice, Geopolitics, Sushi Rice, thick, critic, MLB, existential crisis

    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
    运转
    0.43
    లేదు
    0.42
     spineItem
    0.42
    会社
    0.42
     badań
    0.41
    యన
    0.41
    worlds
    0.41
    뭡
    0.40
    SupportPackage
    0.40
    ্প্র
    0.39
    POSITIVE LOGITS
     onde
    0.52
     ancora
    0.49
    Κα
    0.49
     celebrado
    0.48
     κα
    0.47
    最好的
    0.47
     etiquetas
    0.47
     sicuro
    0.47
     piattaforma
    0.47
    ACLE
    0.46
    Activations Density 0.001%

    No Known Activations