© 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. 1286
    Prev
    Next
    INDEX
    Explanations

    in the

    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
    nhold
    2.50
    𒈬
    2.28
    Zawodnik
    2.24
    캿
    2.20
    狧
    2.19
     tqdm
    2.17
    ኩል
    2.17
    Eds
    2.17
    𝙧
    2.16
    𒀝
    2.15
    POSITIVE LOGITS
     is
    2.02
    .
    2.02
    ,
    2.02
     of
    1.95
     with
    1.86
     and
    1.83
    cross
    1.82
     are
    1.82
     in
    1.79
     give
    1.78
    Activations Density 0.662%

    No Known Activations