© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71707
    Prev
    Next
    INDEX
    Explanations

    Xcode development

    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
     of
    -1.95
     our
    -1.74
    n
    -1.63
    """
    -1.48
    B
    -1.46
    c
    -1.45
    p
    -1.41
    v
    -1.41
     ребен
    -1.39
    I
    -1.37
    POSITIVE LOGITS
     but
    1.54
     hieß
    1.51
     області
    1.50
     it
    1.48
    urando
    1.44
    がありません
    1.43
     Características
    1.41
     arbeitete
    1.38
     something
    1.34
     области
    1.34
    Activations Density 0.148%

    No Known Activations