© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12247
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and self-reference

    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
     likely
    2.37
    likely
    2.09
    নীতিক
    2.08
    蚀
    2.08
    initComponents
    2.05
    ्तीय
    2.03
    erView
    2.02
    可能会
    1.98
    erman
    1.96
     implications
    1.96
    POSITIVE LOGITS
    ein
    1.98
    i
    1.92
    ei
    1.91
    S
    1.79
    y
    1.74
    en
    1.73
    <code>
    1.72
    에
    1.71
    툰
    1.70
    o
    1.68
    Activations Density 0.053%

    No Known Activations