© 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. 10-GEMMASCOPE-RES-131K
    7. 118851
    Prev
    Next
    INDEX
    Explanations

    pool or pooling

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

    The neuron fires on occurrences of the identifier “Pool” (and closely related forms like “pool,” “Pooled,” or “PoolConfig”) in source code.

    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
     we
    -2.98
    
    -2.53
    椟
    -2.38
    肏
    -2.27
    PreferredItem
    -2.05
    倏
    -1.98
    が付いて
    -1.94
     worrying
    -1.91
     perfetta
    -1.88
    袅
    -1.88
    POSITIVE LOGITS
    ㉗
    2.59
    _
    2.38
    \
    2.31
    at
    2.19
    私の
    2.17
     gelb
    2.13
    𓆜
    2.09
    тся
    2.06
    (
    2.06
    ––
    2.02
    Activations Density 0.005%

    No Known Activations