© 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. 129439
    Prev
    Next
    INDEX
    Explanations

    August followed by date

    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
     diciendo
    -2.63
     recibiendo
    -2.48
     intentando
    -2.41
     escribiendo
    -2.33
    exemple
    -2.30
    沕
    -2.27
    ࠬ
    -2.25
    菀
    -2.22
    ERICAN
    -2.22
    ,’
    -2.22
    POSITIVE LOGITS
    p
    2.94
    \
    2.92
    The
    2.77
    In
    2.75
    b
    2.67
    h
    2.64
    k
    2.58
    w
    2.56
    ."
    2.53
     {
    2.44
    Activations Density 0.004%

    No Known Activations