© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56996
    Prev
    Next
    INDEX
    Explanations

    3D virtual rendering and reconstruction

    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
    thun
    -0.87
    trooper
    -0.82
    matchCondition
    -0.81
     hmm
    -0.81
    tivation
    -0.79
     triun
    -0.77
    QMetaType
    -0.77
     Peterborough
    -0.77
     Pristup
    -0.76
     съдържа
    -0.76
    POSITIVE LOGITS
     virtual
    2.02
     simulation
    1.73
    virtual
    1.68
     animation
    1.63
     simulations
    1.61
     computer
    1.57
     render
    1.56
     rendering
    1.55
     Virtual
    1.53
     visualization
    1.51
    Activations Density 0.075%

    No Known Activations