© 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-16K
    7. 8332
    Prev
    Next
    INDEX
    Explanations

    plot layout adjustment

    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_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
    -​
    1.19
    urat
    1.16
    ments
    1.16
    deb
    1.15
     Ши
    1.15
    sst
    1.15
     contractual
    1.15
    ­
    1.11
    iots
    1.11
     irre
    1.10
    POSITIVE LOGITS
     tzv
    1.24
    ৈতিক
    1.20
     próprio
    1.18
     propio
    1.15
     Choibalsan
    1.15
     amelyek
    1.14
     Selatan
    1.13
     velmi
    1.12
     propia
    1.11
     ótimo
    1.11
    Activations Density 0.022%

    No Known Activations