© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38940
    Prev
    Next
    INDEX
    Explanations

    daily commute to work or school

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :'',
    -1.12
     cualquier
    -1.06
    话音
    -1.02
    writeString
    -1.02
    Trichloroethane
    -1.01
     пользователя
    -0.98
     supuesto
    -0.97
    anças
    -0.97
     SEVENT
    -0.95
     cualidades
    -0.95
    POSITIVE LOGITS
     daily
    1.62
     morning
    1.49
     everyday
    1.46
     commute
    1.45
     school
    1.37
     every
    1.33
     commuting
    1.22
     déjeuner
    1.13
     from
    1.13
     work
    1.13
    Activations Density 0.026%

    No Known Activations