© 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. 1405
    Prev
    Next
    INDEX
    Explanations

    saving files

    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
    lets
    2.08
    <bos>
    2.01
    s
    2.00
    re
    1.91
    air
    1.84
    rations
    1.83
    uit
    1.81
    ily
    1.79
    suits
    1.78
    uses
    1.74
    POSITIVE LOGITS
    놁
    3.59
     sécrétion
    3.54
    娍
    3.35
    潛行遊戲
    3.34
     glPopMatrix
    3.33
    벍
    3.29
     ŝ
    3.29
     pédicule
    3.29
     REGIUNI
    3.28
    okatokat
    3.26
    Activations Density 0.044%

    No Known Activations