© 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. 10-GEMMASCOPE-RES-131K
    7. 100565
    Prev
    Next
    INDEX
    Explanations

    cancer risk and related conditions

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

    mentions of diseases, particularly cancer and other medical conditions.

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

    This neuron detects mentions of specific cancers (e.g., breast, colorectal, lung, prostate).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     säkert
    -1.41
    stdbool
    -1.36
     ändå
    -1.34
     huset
    -1.27
     educativa
    -1.26
    嚷
    -1.24
    クロー
    -1.23
     verdaderos
    -1.21
    ियां
    -1.21
     antiguos
    -1.21
    POSITIVE LOGITS
     when
    1.49
     like
    1.48
     in
    1.41
     by
    1.38
     while
    1.37
     during
    1.37
     alongside
    1.23
     and
    1.22
     into
    1.21
     would
    1.20
    Activations Density 0.331%

    No Known Activations