© 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. 12035
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    czą
    -0.85
     desconto
    -0.84
    々
    -0.82
     algun
    -0.82
    ilage
    -0.81
     ITIS
    -0.80
    eleri
    -0.80
    ᄋ
    -0.79
     Haziran
    -0.79
    zości
    -0.79
    POSITIVE LOGITS
     number
    8.19
    number
    5.00
     número
    4.41
    Number
    4.13
     Number
    4.13
    NUMBER
    3.84
     число
    3.78
     aantal
    3.77
     NUMBER
    3.73
     Anzahl
    3.72
    Activations Density 0.303%

    No Known Activations