© 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. 34-GEMMASCOPE-RES-131K
    7. 98460
    Prev
    Next
    INDEX
    Explanations

    border lines and boundaries

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

    The neuron is detecting short prepositional phrases indicating location or source—e.g. “of the court,” “along the base,” “from the command line.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    cú
    -0.90
    Ingredients
    -0.88
    ♠
    -0.79
    endfor
    -0.75
     nore
    -0.75
     répondu
    -0.75
     réussi
    -0.75
    Réponse
    -0.74
    区間
    -0.74
     humaines
    -0.73
    POSITIVE LOGITS
     line
    1.70
     midline
    1.41
     línea
    1.41
     centerline
    1.34
     خط
    1.33
    CommandLine
    1.27
     baseline
    1.24
     garis
    1.16
     линия
    1.09
     ligne
    1.06
    Activations Density 0.058%

    No Known Activations