© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 23
    Prev
    Next
    INDEX
    Explanations

    subtle actions and feelings

    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
    年月
    1.41
     Visitation
    1.39
    outfile
    1.31
    _{,
    1.30
     weekends
    1.27
    weekend
    1.26
     visitation
    1.23
    Ϯ
    1.21
    jsonData
    1.20
     geschaffen
    1.19
    POSITIVE LOGITS
     smirk
    1.46
     gesturing
    1.46
     shrug
    1.42
     jerk
    1.40
     nods
    1.39
     nod
    1.38
     crou
    1.37
     waved
    1.36
     shake
    1.34
     blush
    1.34
    Activations Density 2.109%

    No Known Activations