© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 613
    Prev
    Next
    INDEX
    Explanations

    Per received, Prater, Plakinastrella, Kohati, Guava, Geopolitical

    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
    1.46
    น้อง
    1.41
     Fasc
    1.39
    לך
    1.36
     изоли
    1.35
    みんな
    1.30
     Liebe
    1.22
     Prensa
    1.20
    setHorizontal
    1.19
     поз
    1.19
    POSITIVE LOGITS
     enlightening
    1.45
     $)$.
    1.35
     অধিবেশ
    1.35
     benchmarking
    1.33
    adan
    1.33
    uft
    1.31
    ールの
    1.30
    <0xBF>
    1.30
    vey
    1.30
     শিক্ষার্থীরা
    1.29
    Activations Density 0.884%

    No Known Activations