© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82835
    Prev
    Next
    INDEX
    Explanations

    special characters and license text

    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_34/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
     frases
    -0.87
     глу
    -0.79
    رفی
    -0.76
    Any
    -0.75
    zeige
    -0.75
    亚马逊
    -0.73
     Qualquer
    -0.73
    Other
    -0.73
     any
    -0.73
    ویز
    -0.72
    POSITIVE LOGITS
     Hough
    0.88
    angdong
    0.80
    zupeł
    0.79
     nex
    0.78
     dịch
    0.78
    beiten
    0.77
     behavi
    0.77
    ensation
    0.76
     gemeente
    0.74
    钱
    0.74
    Activations Density 0.036%

    No Known Activations