© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39119
    Prev
    Next
    INDEX
    Explanations

    code elements and variables

    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
     siinä
    -0.90
    指针
    -0.88
    dó
    -0.85
                      
    -0.84
    ilangkan
    -0.84
     erila
    -0.83
     Chbosky
    -0.82
     kaikki
    -0.82
     Juifs
    -0.82
    enseignements
    -0.81
    POSITIVE LOGITS
     aforesaid
    0.85
    iferous
    0.80
     to
    0.80
    tronics
    0.79
     peru
    0.77
     シリーズ
    0.76
    ẹo
    0.76
    Outros
    0.76
    Problemas
    0.75
    OFFICIAL
    0.75
    Activations Density 0.006%

    No Known Activations