© 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. 14750
    Prev
    Next
    INDEX
    Explanations

    similar wording or models

    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
    ங்கிணை
    2.63
    د
    2.56
    ه
    2.29
    ल्याण
    2.22
    uert
    2.21
    rester
    2.17
    tson
    2.17
    هَا
    2.16
    طه
    2.16
    ills
    2.14
    POSITIVE LOGITS
    侶
    2.66
    בק
    2.52
    hman
    2.51
    惧
    2.51
     обстоя
    2.48
    భ్య
    2.32
    淌
    2.22
    MENTS
    2.20
    ̀
    2.19
     reside
    2.19
    Activations Density 0.014%

    No Known Activations