© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1364
    Prev
    Next
    INDEX
    Explanations

    noun compounds of specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    Е
    0.46
     inwardly
    0.44
    Не
    0.44
     incom
    0.44
    oshape
    0.44
    И
    0.43
    Phe
    0.43
    Diameter
    0.43
    Importance
    0.42
     objectivity
    0.42
    POSITIVE LOGITS
    /
    0.66
     cookies
    0.64
     beverages
    0.62
     linens
    0.58
     cinco
    0.58
     geothermal
    0.57
     memorabilia
    0.57
     mascotas
    0.57
     bebidas
    0.57
     headphones
    0.56
    Activations Density 0.004%

    No Known Activations