© 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. 30731
    Prev
    Next
    INDEX
    Explanations

    digits and letters R, K, T

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

    tesseract, Navarathri, Windows, stablelm, example.com, icons

    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
     testAvg
    0.38
     dilwale
    0.37
     stockno
    0.35
     resTmp
    0.35
    𒁁
    0.34
     پسر
    0.34
     xhrObj
    0.34
     chłop
    0.34
     QuantityOnHand
    0.34
     اتار
    0.33
    POSITIVE LOGITS
    -
    0.59
    D
    0.49
    K
    0.48
    E
    0.48
    L
    0.48
    W
    0.47
    1
    0.47
    4
    0.46
    c
    0.45
    P
    0.45
    Activations Density 0.006%

    No Known Activations