© 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. 2820
    Prev
    Next
    INDEX
    Explanations

    license clauses

    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
     Пав
    -0.77
    soni
    -0.73
     orari
    -0.68
    lysninger
    -0.67
    pension
    -0.67
     bör
    -0.66
     whine
    -0.66
     commune
    -0.66
     transistors
    -0.66
    Laporan
    -0.65
    POSITIVE LOGITS
    Reform
    0.70
    /#
    0.69
    FullScreen
    0.68
    ({\
    0.65
    мен
    0.64
    Cousin
    0.64
    ทำให้
    0.64
    룹
    0.64
    แต่ง
    0.64
     King
    0.63
    Activations Density 0.081%

    No Known Activations