© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2127
    Prev
    Next
    INDEX
    Explanations

    g followed by punctuation

    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_13_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
     (
    2.86
     ([
    2.46
     .(
    2.44
     ((
    2.37
     (.
    2.33
     ('
    2.32
     (~
    2.21
    (
    2.18
     _{(
    2.14
     的
    2.11
    POSITIVE LOGITS
    első
    2.25
    ósz
    2.23
    Vý
    2.19
    %);
    2.05
    stylesheet
    2.04
    )$;
    2.03
    ährend
    2.01
    )،
    1.98
    osság
    1.97
    ésus
    1.97
    Activations Density 0.228%

    No Known Activations