© 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. 60203
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code symbols

    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
     and
    -1.92
     blissful
    -1.84
    Every
    -1.81
     beweging
    -1.77
     schnellen
    -1.76
     through
    -1.76
    amaan
    -1.74
    \[
    -1.73
     during
    -1.72
    冏
    -1.72
    POSITIVE LOGITS
     the
    2.53
     débuts
    2.09
     myriad
    1.97
     be
    1.92
    et
    1.68
    ently
    1.68
     extremely
    1.67
      
    1.66
     ตัว
    1.66
     REALLY
    1.65
    Activations Density 0.060%

    No Known Activations