© 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. 250898
    Prev
    Next
    INDEX
    Explanations

    noun phrases and descriptions

    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
    Domic
    0.51
    📂
    0.50
    एफ
    0.49
    žete
    0.48
    Uploaded
    0.48
    RowNum
    0.47
    Tarjeta
    0.46
    garian
    0.46
    ▬▬
    0.46
    🔗
    0.46
    POSITIVE LOGITS
     be
    0.54
     poetry
    0.52
     quilting
    0.52
     knitting
    0.51
     ẞ
    0.51
     riding
    0.50
     sewing
    0.50
     quilts
    0.50
     evaluation
    0.50
     books
    0.50
    Activations Density 0.000%

    No Known Activations