© 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. 1852
    Prev
    Next
    INDEX
    Explanations

    ARKit projects

    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
     Especial
    -0.73
     Pieter
    -0.72
    Tác
    -0.71
     accidente
    -0.69
     warmly
    -0.69
     retired
    -0.69
    Կ
    -0.69
    collapsed
    -0.69
    блиоте
    -0.68
     inexist
    -0.67
    POSITIVE LOGITS
     AR
    1.20
    AR
    1.04
     tracking
    0.98
     Plane
    0.93
    IKEA
    0.90
    Plane
    0.89
    plane
    0.88
     tracked
    0.87
    Planes
    0.87
     IKEA
    0.86
    Activations Density 0.018%

    No Known Activations