© 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. 91594
    Prev
    Next
    INDEX
    Explanations

    neck and associated conditions

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

    references to the neck and neck-related terms in medical and anatomical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron specifically activates on the substring “neck” (including in compounds like “neck pain” or “neck‐snapping”).

    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
    サイト
    -0.90
     been
    -0.88
     зви
    -0.85
    failures
    -0.85
     contentType
    -0.84
     Mx
    -0.84
    äts
    -0.83
     Confidentiality
    -0.80
     skips
    -0.80
     Marching
    -0.80
    POSITIVE LOGITS
    beard
    1.11
    laced
    1.09
    tie
    1.05
    ties
    0.96
    lace
    0.87
     Sna
    0.84
    lacing
    0.84
    orique
    0.83
    lines
    0.82
     stiffness
    0.82
    Activations Density 0.014%

    No Known Activations