© 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. 108993
    Prev
    Next
    INDEX
    Explanations

    projected images and displays

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags terms having to do with projecting or displaying visual content (e.g. holograms, video projection, rear‐projection displays).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Braille
    -0.81
    barcelona
    -0.77
    oneta
    -0.77
    hif
    -0.76
    setVisibility
    -0.75
    čaj
    -0.75
    parcel
    -0.74
    bangunan
    -0.73
    澡
    -0.73
    ärna
    -0.72
    POSITIVE LOGITS
     projected
    4.25
     projection
    3.97
     projections
    3.69
    projected
    3.56
    projection
    3.42
    Projected
    3.39
     Projected
    3.23
     Projection
    3.22
    Projection
    3.20
     projecting
    3.17
    Activations Density 0.039%

    No Known Activations