© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13919
    Prev
    Next
    INDEX
    Explanations

    digital twins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    ecimento
    1.83
    ening
    1.75
    た
    1.73
     silently
    1.72
     pleasantly
    1.66
     screened
    1.63
    忡
    1.63
    ೂರ್ವ
    1.62
    闱
    1.60
    en
    1.55
    POSITIVE LOGITS
    зни
    2.22
    도로
    2.13
     Logistics
    2.08
    Gust
    2.03
    땔
    2.01
    assertInstanceOf
    2.01
    도의
    1.97
    Integral
    1.96
    짖
    1.96
     appendage
    1.95
    Activations Density 0.026%

    No Known Activations