© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5081
    Prev
    Next
    INDEX
    Explanations

    web pages and development

    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_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
    ted
    3.46
    nya
    3.19
    了
    2.95
    ti
    2.92
    s
    2.82
    t
    2.79
    다고
    2.72
    ness
    2.67
    tio
    2.65
    tions
    2.63
    POSITIVE LOGITS
     cotidiana
    2.36
    actory
    2.34
    瓣
    2.32
    AsUpIndicator
    2.16
    ゞ
    2.13
    敎
    2.11
    롭게
    2.07
     задание
    2.05
    丂
    2.04
     __(
    2.03
    Activations Density 0.215%

    No Known Activations