© 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. 57251
    Prev
    Next
    INDEX
    Explanations

    version numbers, dates, and code snippets

    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
     responsible
    -0.92
     Besten
    -0.85
     how
    -0.85
     why
    -0.84
     estadia
    -0.83
    cyklo
    -0.78
    倪
    -0.77
    algebras
    -0.75
     already
    -0.74
    nąć
    -0.74
    POSITIVE LOGITS
    heiten
    0.93
    inary
    0.87
     stessi
    0.86
    첵
    0.85
    ceous
    0.85
     polisi
    0.85
    toolStripButton
    0.84
    所说的
    0.84
    难受
    0.84
    скар
    0.84
    Activations Density 0.001%

    No Known Activations