© 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. 13567
    Prev
    Next
    INDEX
    Explanations

    stealth

    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
    事的
    2.30
    ጠር
    2.27
     sûr
    2.16
    اری
    2.12
    ĵo
    2.07
     vjer
    2.05
    ĵ
    2.04
    arnas
    2.04
    ූර්
    2.02
     znan
    1.99
    POSITIVE LOGITS
    e
    2.10
    া
    2.05
    iiv
    2.05
     anchors
    1.97
     불구하고
    1.95
    ing
    1.93
    y
    1.91
    traf
    1.84
    ی
    1.83
    i
    1.83
    Activations Density 0.024%

    No Known Activations