© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11626
    Prev
    Next
    INDEX
    Explanations

    biomedical sciences

    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
     phenotype
    1.29
    Masukkan
    1.20
    קת
    1.19
     Extensive
    1.19
    𐱅
    1.17
    Chemical
    1.17
    genetic
    1.17
     रासायनिक
    1.16
     phenotypic
    1.14
    ochemical
    1.14
    POSITIVE LOGITS
    プト
    0.81
     passions
    0.80
     satisfacción
    0.79
     pleasures
    0.77
     disfr
    0.76
     Saturn
    0.76
     здраво
    0.76
     победи
    0.75
     diversión
    0.75
    惭
    0.75
    Activations Density 0.001%

    No Known Activations