© 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. 89773
    Prev
    Next
    INDEX
    Explanations

    cell followed by various words

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

    scientific journal and publication terminology related to cell biology.

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

    The neuron activates on any occurrence of the word “cell” (in titles, journal names, or general text).

    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
    ሕ
    -0.77
     narcotic
    -0.77
    reinforced
    -0.74
    oons
    -0.73
    cun
    -0.72
    跛
    -0.71
    יף
    -0.71
    animo
    -0.71
     高等
    -0.71
     Remix
    -0.70
    POSITIVE LOGITS
    ínas
    0.81
     Tissue
    0.80
    ♗
    0.75
    Death
    0.72
    Begin
    0.71
    letal
    0.71
     Hate
    0.70
     Header
    0.69
    Header
    0.69
     apre
    0.68
    Activations Density 0.044%

    No Known Activations