© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 248821
    Prev
    Next
    INDEX
    Explanations

    identifying professionals and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     مکان
    0.46
     cáo
    0.45
    ка
    0.45
    prices
    0.45
    ер
    0.44
     decked
    0.44
     abstracted
    0.44
    บ
    0.44
    㤟
    0.43
    ან
    0.43
    POSITIVE LOGITS
     eigenen
    0.52
     eigene
    0.50
    ätta
    0.48
    റുക
    0.45
     eigener
    0.45
    eigen
    0.44
     own
    0.44
    ängt
    0.43
     samarbe
    0.43
     ganglion
    0.43
    Activations Density 0.003%

    No Known Activations