© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58024
    Prev
    Next
    INDEX
    Explanations

    oncogenes and proto-oncogenes

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

    This neuron detects mentions of oncogenes, particularly c-myc, and cancer-related genetic terminology.

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

    The neuron detects occurrences of oncogene or proto-oncogene names—especially those with “c-” or similar gene-prefix patterns (e.g. c-myc, c-fos, p53, ras, etc.).

    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
    olian
    -0.78
    xido
    -0.76
    WEBPACK
    -0.74
    logii
    -0.71
     ADN
    -0.71
    emann
    -0.71
     Hawthorne
    -0.70
    𝓴
    -0.70
     Kantor
    -0.70
     hag
    -0.68
    POSITIVE LOGITS
     onco
    1.64
     proto
    1.44
     amplification
    1.20
    proto
    1.18
     Proto
    1.02
     Onco
    1.01
    Proto
    1.01
     ampli
    0.98
     amplified
    0.89
    PROTO
    0.85
    Activations Density 0.177%

    No Known Activations