© 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. 725
    Prev
    Next
    INDEX
    Explanations

    Exceptional or outstanding achievements

    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
    h
    1.24
    る
    1.16
    er
    1.15
    ing
    1.11
    t
    1.07
    y
    1.07
    tul
    1.04
    e
    1.04
    al
    1.01
    bore
    1.01
    POSITIVE LOGITS
     resident
    0.93
    годня
    0.88
     ‘
    0.86
     lively
    0.85
    енти
    0.85
    チール
    0.84
    inskii
    0.83
     biggest
    0.83
     latest
    0.82
    ゙
    0.81
    Activations Density 0.596%

    No Known Activations