© 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. 43753
    Prev
    Next
    INDEX
    Explanations

    NullPointerException

    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
    裢
    -1.86
     praktische
    -1.73
     -(
    -1.61
    iseaux
    -1.58
     uſe
    -1.56
     Atención
    -1.55
    ama
    -1.52
     ["
    -1.52
     revisa
    -1.51
    ཿ
    -1.49
    POSITIVE LOGITS
    when
    1.76
     widespread
    1.69
     noticeable
    1.67
    还有一
    1.63
     tedious
    1.62
     because
    1.62
    
    1.62
     substantial
    1.59
    日時
    1.57
    槃
    1.56
    Activations Density 0.025%

    No Known Activations