© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3533
    Prev
    Next
    INDEX
    Explanations

    metal and materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     profundamente
    1.11
    (/^\
    1.01
    రుపు
    0.97
    왠
    0.95
     nenhuma
    0.95
    visor
    0.93
     aquela
    0.93
    traditional
    0.91
    scss
    0.91
    Suddenly
    0.90
    POSITIVE LOGITS
    anguage
    2.54
     halide
    2.46
    製の
    2.36
    制品
    2.23
    製
    2.18
    insertAdjacent
    2.17
    anguages
    2.12
     koop
    2.10
     бом
    2.07
    isers
    2.05
    Activations Density 0.391%

    No Known Activations