© 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. 22-GEMMASCOPE-RES-131K
    7. 70712
    Prev
    Next
    INDEX
    Explanations

    glob, separators, and numbers

    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_22/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
     but
    -0.88
     merkwür
    -0.82
     tatsäch
    -0.78
    ümüş
    -0.77
     eigentliche
    -0.77
    historie
    -0.75
    inguez
    -0.75
    สอง
    -0.74
     pesos
    -0.74
     berfungsi
    -0.73
    POSITIVE LOGITS
     ziekte
    0.88
    itl
    0.82
     gins
    0.82
     curent
    0.82
     nonprofit
    0.80
     ép
    0.80
    lola
    0.80
     verwalten
    0.80
    iect
    0.79
    𝖒
    0.79
    Activations Density 0.016%

    No Known Activations