© 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. 824
    Prev
    Next
    INDEX
    Explanations

    tools and associated items

    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
     of
    1.62
    '
    1.45
    -
    1.18
     ofthe
    1.14
    board
    1.13
    ’
    1.08
    ine
    1.08
    of
    1.06
    boards
    1.04
     only
    1.02
    POSITIVE LOGITS
     geométricas
    1.92
     conecta
    1.86
    燡
    1.85
    Ꮂ
    1.81
     niewiel
    1.80
     duże
    1.77
    峒
    1.77
     Wochschr
    1.77
    рёх
    1.77
    ﺖ
    1.76
    Activations Density 0.262%

    No Known Activations