© 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. 42212
    Prev
    Next
    INDEX
    Explanations

    flange

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

    The neuron strongly activates on occurrences of the mechanical‐engineering term “flange” (and close variants like “flanged” or its subword “flang”).

    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
     стоковая
    -3.28
    蹚
    -2.89
    n
    -2.80
    儅
    -2.80
    鰨
    -2.72
    曏
    -2.70
     ſch
    -2.67
    臯
    -2.64
    槼
    -2.63
    袮
    -2.61
    POSITIVE LOGITS
     '
    2.59
    '
    2.58
     amicable
    2.52
    </b>
    2.42
    ;
    2.41
     --
    2.36
     fazer
    2.33
     ---
    2.23
     cordial
    2.14
    
    2.13
    Activations Density 0.001%

    No Known Activations