© 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. 92091
    Prev
    Next
    INDEX
    Explanations

    cancer treatment resistance

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

    scientific content related to cancer research, treatment, and prevention.

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

    The neuron is tracking how far into the text you are—its activation grows steadily with token position, so it effectively marks “later” or “farther along” words in a document.

    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
     Enfer
    -0.78
     mineures
    -0.78
    wants
    -0.76
    NTSTATUS
    -0.76
    ρω
    -0.76
     компен
    -0.76
     injector
    -0.75
     штра
    -0.75
    rophilic
    -0.74
    randint
    -0.74
    POSITIVE LOGITS
     cancer
    1.62
    cancer
    1.45
    Cancer
    1.40
     Cancer
    1.39
     tumor
    1.17
     CANCER
    1.12
    tumor
    1.09
     prostate
    1.03
     breast
    0.97
     down
    0.96
    Activations Density 0.288%

    No Known Activations