© 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. 63720
    Prev
    Next
    INDEX
    Explanations

    microsoft spatial mixed reality

    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
     entreat
    -0.79
     unusual
    -0.75
    ndares
    -0.73
    文中
    -0.69
    ន
    -0.69
     Maroon
    -0.69
     unusually
    -0.68
     carpentry
    -0.68
    中島
    -0.68
     prismatic
    -0.67
    POSITIVE LOGITS
     Azure
    0.93
    microsoft
    0.92
    conto
    0.89
     Spatial
    0.85
     Dynamics
    0.85
     QU
    0.85
     Microsoft
    0.85
    ocu
    0.84
    tracked
    0.82
     Han
    0.81
    Activations Density 0.008%

    No Known Activations