© 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-65K
    7. 1698
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by list item

    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_65k_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
     zigzag
    1.24
    답니다
    1.23
     namesake
    1.21
     niobium
    1.18
    ന്തപു
    1.16
    <unused1896>
    1.14
    𒋼
    1.14
    <unused1727>
    1.13
    娠
    1.13
     perg
    1.12
    POSITIVE LOGITS
    Additionally
    1.23
    Although
    1.22
    ;
    1.22
    ،
    1.20
    However
    1.16
     Additionally
    1.14
    Despite
    1.13
    Moreover
    1.13
    //
    1.11
    In
    1.11
    Activations Density 0.555%

    No Known Activations