© 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. 34821
    Prev
    Next
    INDEX
    Explanations

    circle geometry

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

    The neuron activates on occurrences of “circle” (and close variants like “Circular”).

    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
     they
    -2.84
    眛
    -2.59
    栒
    -2.33
    瀦
    -2.25
    を観
    -2.13
    籀
    -2.13
    slightly
    -2.11
    orghini
    -2.11
     améli
    -2.09
    
    -2.09
    POSITIVE LOGITS
    "،
    2.77
     että
    2.38
    шего
    2.38
    er
    2.34
     Ganzen
    2.33
     selben
    2.31
    dagogik
    2.31
     bús
    2.31
     voetballer
    2.31
    of
    2.30
    Activations Density 0.018%

    No Known Activations