© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2525
    Prev
    Next
    INDEX
    Explanations

    are struggling

    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_17_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
    ĕç
    1.09
    glightbox
    1.08
    ὸς
    1.07
    <unused1067>
    1.07
    <unused390>
    1.07
    <unused556>
    1.05
    <unused653>
    1.05
    <unused369>
    1.04
    <unused220>
    1.03
    <unused429>
    1.03
    POSITIVE LOGITS
    :
    4.98
    :-
    4.48
    ：
    4.32
    :*
    4.18
    :.
    4.06
    :<
    4.02
    :[
    3.91
    :(
    3.90
     :
    3.87
    .:
    3.86
    Activations Density 1.866%

    No Known Activations