© 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. 188184
    Prev
    Next
    INDEX
    Explanations

    marketing strategy, it slowly, city, nationwide, comments, phone, centuries

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

    technical specifications or features

    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
    婕
    0.57
     utilidad
    0.52
     coordinador
    0.52
     gegevens
    0.48
     contextos
    0.48
    薏
    0.48
     effetto
    0.47
     aspett
    0.47
     límites
    0.47
     accessoires
    0.47
    POSITIVE LOGITS
     Falls
    0.52
     Merchant
    0.52
     สู
    0.51
    洖
    0.50
     ทำ
    0.49
     Prussia
    0.49
     Creek
    0.48
     Kafka
    0.47
     Woll
    0.47
     pror
    0.47
    Activations Density 0.001%

    No Known Activations