© 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. 16378
    Prev
    Next
    INDEX
    Explanations

    conjunctions and lists

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

    lists and conjunctions

    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
    /
    0.55
    0.42
    int
    0.42
    があった
    0.40
    が出来
    0.37
    ayu
    0.36
    //
    0.36
    att
    0.36
    Aff
    0.35
    です
    0.35
    POSITIVE LOGITS
    -,
    0.73
    以及
    0.60
     તેમજ
    0.60
     비롯
    0.59
     oraz
    0.57
     、,
    0.57
     sowie
    0.57
     그리고
    0.55
     valamint
    0.55
    ,...,
    0.55
    Activations Density 0.032%

    No Known Activations