© 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. 14686
    Prev
    Next
    INDEX
    Explanations

    Fine Arts

    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
    s
    4.26
    nya
    3.33
    いる
    3.27
    ों
    3.24
    dte
    3.08
    nemen
    3.01
    了
    2.94
    nl
    2.86
    selen
    2.85
    ncia
    2.84
    POSITIVE LOGITS
    ̀n
    2.63
    HANDLE
    2.08
    ག
    2.05
    ۰۰
    2.05
    ŋ
    2.05
    fromCharCode
    2.05
    とな
    2.04
    Sent
    2.01
    حي
    2.01
     taas
    2.01
    Activations Density 0.010%

    No Known Activations