© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49390
    Prev
    Next
    INDEX
    Explanations

    CERN Collider

    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
     pungkas
    -0.68
     National
    -0.65
     Center
    -0.65
     Leighton
    -0.65
    ارا
    -0.64
    ására
    -0.64
    Cual
    -0.63
    XZ
    -0.62
     in
    -0.61
    itunes
    -0.61
    POSITIVE LOGITS
     CERN
    1.94
    CERN
    1.68
    cern
    1.16
     Geneva
    1.09
     ATLAS
    1.05
    LHC
    1.04
     LHC
    1.01
    Particle
    0.87
     Mey
    0.85
    Prun
    0.85
    Activations Density 0.039%

    No Known Activations