© 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. 34-GEMMASCOPE-RES-131K
    7. 57337
    Prev
    Next
    INDEX
    Explanations

    combining accents and marks

    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_34/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
    czu
    -0.82
     ditangkap
    -0.77
     Ear
    -0.76
    Ѕ
    -0.73
    әм
    -0.71
     Üniversitesi
    -0.70
    octet
    -0.70
     einde
    -0.69
     metropolitan
    -0.69
    ([])
    -0.69
    POSITIVE LOGITS
     accents
    1.33
     accent
    1.25
     marks
    1.08
     COMBIN
    1.05
    accent
    1.03
    Combining
    1.02
     combining
    0.95
    diac
    0.94
    ◌
    0.92
    combin
    0.91
    Activations Density 0.038%

    No Known Activations