© 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. 98693
    Prev
    Next
    INDEX
    Explanations

    code and structured text delimiters

    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
     strength
    -0.80
     potencial
    -0.79
    strength
    -0.77
     hipote
    -0.72
    blom
    -0.72
     potenci
    -0.70
     croce
    -0.69
     startX
    -0.68
     цело
    -0.67
     Strength
    -0.66
    POSITIVE LOGITS
     Fordham
    0.77
     csak
    0.73
     egyik
    0.68
    トライ
    0.67
    Drama
    0.66
     TextAppearance
    0.66
     nymph
    0.66
     незавершена
    0.66
     Adviser
    0.65
    尼斯
    0.65
    Activations Density 0.047%

    No Known Activations