© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8004
    Prev
    Next
    INDEX
    Explanations

    mitochondrial cell function

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

    The neuron detects references to mitochondria and mitochondrial functions in scientific text.

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

    This neuron activates on mentions of mitochondria (e.g., “mitochondrial” or “mitochondria”).

    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
    倥
    -2.92
    樒
    -2.67
     kveld
    -2.61
    י
    -2.59
    ه‌ای
    -2.58
    ي
    -2.52
     rekke
    -2.42
    需要
    -2.41
    是一个
    -2.33
    ed
    -2.31
    POSITIVE LOGITS
    It
    2.44
    鋅
    2.30
    ︲
    2.28
    玧
    2.16
    行って
    2.13
     وإ
    2.06
    踌
    2.02
    箆
    2.00
    
    1.99
     It
    1.98
    Activations Density 0.007%

    No Known Activations