© 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. 22-GEMMASCOPE-RES-131K
    7. 33179
    Prev
    Next
    INDEX
    Explanations

    programming constructs and keywords

    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
     erweiter
    -0.94
    Iš
    -0.93
     erfolgreichen
    -0.90
     Inhalten
    -0.89
     Fähig
    -0.88
    openhauer
    -0.87
    moments
    -0.85
    Enciclopedia
    -0.85
     そば
    -0.84
     Erfolgs
    -0.84
    POSITIVE LOGITS
     tensorflow
    0.82
    blog
    0.79
     собой
    0.79
     means
    0.78
    bi
    0.78
    ตู
    0.77
    制造
    0.77
     score
    0.75
    en
    0.73
     study
    0.73
    Activations Density 0.006%

    No Known Activations