© 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. 10-GEMMASCOPE-RES-131K
    7. 20654
    Prev
    Next
    INDEX
    Explanations

    reading and watching

    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_10/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
    {
    -1.57
    5
    -1.39
     you
    -1.35
    ↵
    -1.34
     Если
    -1.34
     data
    -1.27
    >=
    -1.27
     in
    -1.25
    更に
    -1.24
    ).
    -1.23
    POSITIVE LOGITS
     llevado
    1.36
    ӧ
    1.33
     progresso
    1.30
    Cek
    1.28
     aliado
    1.27
    escalier
    1.27
     černá
    1.25
     šed
    1.23
     znamená
    1.22
     feststellen
    1.22
    Activations Density 0.058%

    No Known Activations