© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65710
    Prev
    Next
    INDEX
    Explanations

    data underlying

    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
    ouflage
    -0.81
    حول
    -0.80
    šana
    -0.80
     zawier
    -0.80
    Atsauces
    -0.74
     теря
    -0.73
     Zugriff
    -0.72
    网络
    -0.70
     bestätigt
    -0.70
     milioni
    -0.69
    POSITIVE LOGITS
     Epp
    0.88
     recens
    0.81
     negroes
    0.81
     brz
    0.81
    expects
    0.79
     bâ
    0.79
     pp
    0.78
    Ming
    0.77
     relig
    0.76
     Jam
    0.76
    Activations Density 0.000%

    No Known Activations