© 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. 117143
    Prev
    Next
    INDEX
    Explanations

    Cognitive application paths

    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
     Channing
    -0.75
     нах
    -0.71
    ify
    -0.68
     tors
    -0.67
    στή
    -0.67
     Jacobi
    -0.67
     FormControl
    -0.66
    balls
    -0.66
     yard
    -0.65
    त्या
    -0.63
    POSITIVE LOGITS
    の為
    0.71
    üyük
    0.68
    ഭ
    0.68
    Generate
    0.65
    uruh
    0.65
    iencias
    0.64
     day
    0.63
     Kral
    0.63
    PagerAdapter
    0.63
     Brent
    0.63
    Activations Density 0.062%

    No Known Activations