© 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. 66014
    Prev
    Next
    INDEX
    Explanations

    geometric circles and intersections

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

    The neuron activates whenever the word “circles” appears.

    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
    {
    -2.55
    A
    -2.19
    </b>
    -2.13
     want
    -2.09
    ↵↵
    -2.03
     strö
    -2.00
     короб
    -1.97
     и
    -1.95
     reír
    -1.93
     one
    -1.91
    POSITIVE LOGITS
    寕
    2.91
    䊏
    2.72
    ’
    2.69
     mismos
    2.67
    轳
    2.53
    乆
    2.52
    蓐
    2.47
    er
    2.39
    ⧠
    2.38
    ⽥
    2.34
    Activations Density 0.005%

    No Known Activations