© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26035
    Prev
    Next
    INDEX
    Explanations

    Q, POV, Optimal, Development

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

    The neuron strongly activates on numeric coordinate values (especially floating‐point numbers) in SVG/vector path data.

    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
    pentru
    -1.14
    ᥆
    -1.09
     प्रोड
    -1.09
     trifling
    -1.08
    caire
    -1.07
    même
    -1.05
    erobic
    -1.04
    ⃞
    -1.03
     inconce
    -1.03
    +".
    -1.02
    POSITIVE LOGITS
     when
    1.13
     get
    1.10
     When
    1.10
     make
    1.10
     people
    1.09
     do
    1.01
     While
    0.96
     Before
    0.94
     commonly
    0.94
     ebenfalls
    0.93
    Activations Density 0.002%

    No Known Activations