© 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. 108112
    Prev
    Next
    INDEX
    Explanations

    third eye

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

    This neuron detects named points or landmarks—especially ordinal or proper‐noun body or mystical points (e.g. “третий глаз,” “Baihui,” “GV 2”)—often used in acupuncture or spiritual contexts.

    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
     adher
    -0.94
    cangan
    -0.90
    attere
    -0.88
    Riv
    -0.82
    corner
    -0.82
    ßung
    -0.80
     pax
    -0.80
     تنها
    -0.79
     etern
    -0.79
    ๘
    -0.79
    POSITIVE LOGITS
     centers
    1.13
     centres
    1.11
     centre
    1.05
     sixth
    1.02
     located
    1.01
     center
    1.00
     fourth
    0.93
     pusat
    0.92
     Third
    0.92
     six
    0.88
    Activations Density 0.005%

    No Known Activations