© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47618
    Prev
    Next
    INDEX
    Explanations

    apostle, apostolic, epistle, episodic, episcopate, epistem

    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
    のではなく
    -0.78
    Kelebihan
    -0.77
    Vortex
    -0.77
     Gibb
    -0.77
     مسئول
    -0.76
    Redaktion
    -0.75
     bắc
    -0.75
    嘁
    -0.75
    ערכת
    -0.74
    Michel
    -0.74
    POSITIVE LOGITS
     Paul
    0.90
     Павел
    0.81
     General
    0.75
     areas
    0.75
    General
    0.74
     Barlow
    0.73
    Paul
    0.72
    ская
    0.71
    asy
    0.71
     killings
    0.70
    Activations Density 0.026%

    No Known Activations