© 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. 1503
    Prev
    Next
    INDEX
    Explanations

    Google Cloud, Bard

    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
     olev
    2.06
    빗
    2.06
    İM
    2.04
    ⣶
    2.02
    Owin
    1.99
    ᱮ
    1.97
    colorControl
    1.95
    TreeWidgetItem
    1.95
    REPO
    1.95
    numberOfRecords
    1.95
    POSITIVE LOGITS
    ीडी
    2.50
    ⃝
    2.37
    œ
    2.18
    unya
    2.12
    stone
    2.10
    othiaz
    2.09
    灘
    2.07
    гээ
    2.07
    лица
    2.05
    كور
    2.03
    Activations Density 0.174%

    No Known Activations