© 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. 104390
    Prev
    Next
    INDEX
    Explanations

    patterns for words like "size", "mirror", "earning", "nicely"

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

    common phrase collocations

    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
    ort
    0.53
    r
    0.51
    en
    0.48
    bibitem
    0.47
    ordinary
    0.47
    reference
    0.47
    new
    0.46
    Hyper
    0.46
    hort
    0.44
    op
    0.44
    POSITIVE LOGITS
     sungai
    0.52
     debe
    0.50
     serait
    0.49
    愁
    0.47
     semelhante
    0.47
    簀
    0.47
    ⓷
    0.46
     océano
    0.46
     lò
    0.46
     obses
    0.46
    Activations Density 0.001%

    No Known Activations