© 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. 38238
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    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
     its
    -1.08
     their
    -1.01
    зяй
    -0.94
     an
    -0.92
    憶
    -0.90
     as
    -0.88
    ございません
    -0.88
     when
    -0.86
     new
    -0.85
    家を
    -0.84
    POSITIVE LOGITS
     kroppen
    1.01
     stedet
    0.95
     المثال
    0.94
    kezés
    0.91
    λον
    0.90
     mentre
    0.90
    釕
    0.90
    endom
    0.90
    怔
    0.90
     osserva
    0.90
    Activations Density 0.004%

    No Known Activations