© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2029
    Prev
    Next
    INDEX
    Explanations

    head and neck cancer

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

    terms related to head and neck cancer, particularly carcinomas affecting the oral cavity, pharynx, and larynx.

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

    The neuron activates on specific anatomical and cancer‐related terms—particularly head‐and‐neck sites (e.g. pharyngeal, oral) and squamous cell carcinoma.

    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
     abdominal
    -0.98
     Abdominal
    -0.94
    abdominal
    -0.86
     tibial
    -0.83
    modium
    -0.79
     נע
    -0.78
     dung
    -0.74
     femur
    -0.72
     spina
    -0.72
     diarrhoea
    -0.72
    POSITIVE LOGITS
     neck
    1.55
     throat
    1.48
     HPV
    1.37
     tongue
    1.36
    Neck
    1.34
     Neck
    1.32
    HPV
    1.24
     head
    1.21
     Throat
    1.21
    neck
    1.16
    Activations Density 0.203%

    No Known Activations