© 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. 72534
    Prev
    Next
    INDEX
    Explanations

    C void linked list item NSData PyObject unsigned

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

    The neuron fires on open‐parenthesis tokens—i.e. the “(” that begins a function call or definition.

    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
    坚定
    -1.59
    筇
    -1.40
               
    -1.37
        
    -1.30
     COMPOUNDS
    -1.29
     verschiedene
    -1.29
    masalah
    -1.28
    好みの
    -1.26
    https
    -1.20
    acta
    -1.20
    POSITIVE LOGITS
     so
    1.52
     kotlinx
    1.44
     in
    1.41
    ayage
    1.40
     could
    1.40
     sprawia
    1.34
     there
    1.34
     YOUR
    1.34
     when
    1.31
    reditation
    1.30
    Activations Density 0.010%

    No Known Activations