© 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. 22-GEMMASCOPE-RES-131K
    7. 130569
    Prev
    Next
    INDEX
    Explanations

    the neuron detects mentions of the cell-cycle process and related proliferation terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    cell cycle and cancer

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

    This neuron identifies concepts related to cell cycle, proliferation, and cell division processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    咔嚓
    -1.25
     barbati
    -1.22
     oublier
    -1.21
    améliorer
    -1.19
    éviter
    -1.18
    ：……
    -1.16
     tênis
    -1.15
    atteindre
    -1.14
    bilità
    -1.14
     decorativa
    -1.13
    POSITIVE LOGITS
    Ayrıca
    1.38
    Kullan
    1.23
    //----
    1.17
    waitFor
    1.10
     cancer
    1.08
    🐛
    1.08
     燒
    1.06
     oo
    1.05
    ござ
    1.05
    ixante
    1.05
    Activations Density 0.127%

    No Known Activations