© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71641
    Prev
    Next
    INDEX
    Explanations

    particle physics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ة
    -1.92
    ’
    -1.85
    You
    -1.83
    My
    -1.80
       
    -1.79
    .”
    -1.77
    ‘
    -1.68
    An
    -1.67
    —
    -1.61
    ?
    -1.59
    POSITIVE LOGITS
     Když
    1.82
    eryllium
    1.67
    lysm
    1.62
     voeding
    1.60
     todavía
    1.55
     tindakan
    1.55
     to
    1.54
     yavaş
    1.52
    badah
    1.51
     Entonces
    1.50
    Activations Density 0.018%

    No Known Activations