© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14196
    Prev
    Next
    INDEX
    Explanations

    programming code structure keywords

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

    The neuron fires on lines declaring or defining functions or methods (i.e. method signatures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Aceite
    -0.84
     there
    -0.82
    وت
    -0.81
     betreffenden
    -0.75
     Aceite
    -0.74
     previously
    -0.74
    csol
    -0.73
     interés
    -0.72
    inheritDoc
    -0.71
     erwähnten
    -0.71
    POSITIVE LOGITS
    行
    0.87
     defensive
    0.84
     moderated
    0.82
     inode
    0.81
     Defensive
    0.78
    unte
    0.78
     hoof
    0.78
    ں
    0.77
     yum
    0.76
    ̍
    0.76
    Activations Density 0.014%

    No Known Activations