© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10482
    Prev
    Next
    INDEX
    Explanations

    going out or trips

    np_acts-logits-general · gemini-2.5-flash-lite

    outings and trips

    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_40_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
     consomm
    0.43
    歌手
    0.42
    บู
    0.42
     ralent
    0.42
    静
    0.42
     माहौल
    0.39
    SHIP
    0.39
    駐
    0.39
    驻
    0.39
     Moreira
    0.38
    POSITIVE LOGITS
     outings
    1.77
     outing
    1.73
    外出
    1.50
     trips
    1.44
     excursion
    1.36
     excursions
    1.36
     Trips
    1.31
    出门
    1.24
    出去
    1.20
     trip
    1.06
    Activations Density 0.429%

    No Known Activations