© 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. 84601
    Prev
    Next
    INDEX
    Explanations

    Bootstrap components

    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
     Giải
    -0.76
     Innoc
    -0.72
    Programmer
    -0.72
     laço
    -0.71
    calips
    -0.68
     Habs
    -0.68
     patrio
    -0.68
     Siegfried
    -0.68
    ワイト
    -0.67
     нужны
    -0.67
    POSITIVE LOGITS
     bootstrap
    2.31
    bootstrap
    2.00
     bootstra
    1.86
     Bootstrap
    1.84
    Bootstrap
    1.77
     boot
    1.69
    boot
    1.66
     Boot
    1.59
    Boot
    1.47
     pull
    1.43
    Activations Density 0.021%

    No Known Activations