© 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. 77998
    Prev
    Next
    INDEX
    Explanations

    currency and proper nouns

    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
    አ
    -0.75
    resistant
    -0.73
    日本で
    -0.71
    hosa
    -0.71
     Sacra
    -0.70
     اخذ
    -0.69
     Never
    -0.68
    zc
    -0.67
     مكتبه
    -0.67
    fera
    -0.66
    POSITIVE LOGITS
    ctiveness
    0.90
     Terr
    0.85
    Territory
    0.81
     derogatory
    0.79
    viewDid
    0.76
    
    0.76
    zipcode
    0.74
    Diplom
    0.73
    Anak
    0.73
    uts
    0.72
    Activations Density 0.013%

    No Known Activations