© 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. 47681
    Prev
    Next
    INDEX
    Explanations

    hologram, holographic, HoloLens

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

    The neuron responds to mentions of holograms or holography (e.g., “hologram,” “holographic,” “HoloLens”).

    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
    ecas
    -0.77
    Maar
    -0.72
     Macaulay
    -0.71
    žený
    -0.70
    命名
    -0.69
    launched
    -0.68
     âges
    -0.68
     Pott
    -0.67
     nomenclature
    -0.67
     Karsten
    -0.67
    POSITIVE LOGITS
     hologram
    3.17
     holog
    2.98
     holographic
    2.88
     Ho
    2.53
     ho
    2.41
    Ho
    2.33
    ho
    2.02
     holo
    1.97
    holo
    1.88
     Holo
    1.77
    Activations Density 0.059%

    No Known Activations