© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2600
    Prev
    Next
    INDEX
    Explanations

    consists of descriptions and examples

    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_13_width_65k_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
     주요
    1.39
     주로
    1.25
     かわ
    1.25
     보호
    1.19
     dampak
    1.18
     재
    1.18
     함수의
    1.17
     sesuai
    1.17
     최
    1.16
     化学
    1.16
    POSITIVE LOGITS
     that
    1.27
     seeing
    1.15
     if
    1.13
     видеть
    1.13
    seeing
    1.11
    that
    1.10
     when
    1.05
    if
    1.04
     to
    1.04
     tener
    1.02
    Activations Density 0.583%

    No Known Activations