© 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. 956
    Prev
    Next
    INDEX
    Explanations

    python and related commands

    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
    ي
    2.80
    y
    2.80
    ه
    2.77
    e
    2.70
    a
    2.66
    る
    2.61
    u
    2.50
    eu
    2.49
    o
    2.48
    h
    2.34
    POSITIVE LOGITS
     đốc
    2.15
    ность
    2.07
    ニーカー
    1.99
    チール
    1.98
    \\.
    1.97
    thyl
    1.96
    ELTS
    1.96
    ‌ನ
    1.93
    swald
    1.92
    ளாக்
    1.88
    Activations Density 0.454%

    No Known Activations