© 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. 10-GEMMASCOPE-RES-131K
    7. 20085
    Prev
    Next
    INDEX
    Explanations

    control flow keywords

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

    This neuron fires on the first executable statement inside an if/else branch—i.e. the assignment or function‐call lines that follow a conditional.

    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
    atisk
    -1.70
     kabul
    -1.70
     medan
    -1.70
     Lijst
    -1.69
    lgari
    -1.66
     diki
    -1.66
     leur
    -1.66
     bloem
    -1.63
     Réalisation
    -1.61
     Ottobre
    -1.61
    POSITIVE LOGITS
    驀
    2.00
     It
    1.79
     You
    1.78
    瀟
    1.74
     when
    1.71
     The
    1.60
     about
    1.56
     him
    1.55
     vieler
    1.53
    慫
    1.52
    Activations Density 0.009%

    No Known Activations