© 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. 1301
    Prev
    Next
    INDEX
    Explanations

    the recommended or most

    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
    s
    2.64
    n
    2.52
    The
    2.44
    이
    2.36
    This
    2.35
    r
    2.34
     The
    2.28
    ings
    2.28
    ers
    2.16
     This
    2.08
    POSITIVE LOGITS
    apetiti
    3.16
    <unused106>
    3.13
    atthanam
    3.11
    jiwarl
    3.08
    оні
    3.03
    <unused785>
    3.02
    <unused831>
    3.00
    iyatiti
    2.99
    apetva
    2.99
    lwjglVersion
    2.98
    Activations Density 0.285%

    No Known Activations