© 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. 14079
    Prev
    Next
    INDEX
    Explanations

    programming keywords and punctuation

    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
     and
    -0.85
     for
    -0.83
     pronta
    -0.83
    WHEREAS
    -0.79
    िखित
    -0.79
    горит
    -0.79
     для
    -0.77
     READY
    -0.76
    
    -0.75
    setText
    -0.75
    POSITIVE LOGITS
     Cantidad
    1.02
     ciudadano
    1.01
    př
    0.91
     generaciones
    0.91
     Scattering
    0.90
    Қ
    0.90
     universidades
    0.89
     Polsce
    0.89
    windigkeit
    0.88
    Sunflower
    0.88
    Activations Density 0.007%

    No Known Activations