© 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. 34-GEMMASCOPE-RES-131K
    7. 32381
    Prev
    Next
    INDEX
    Explanations

    glowing light

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

    The neuron fires strongly on words describing light or glowing phenomena (e.g., glow, lighted, dot, faint).

    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
    llingwood
    -0.93
    使う
    -0.90
     gevonden
    -0.86
     Spisak
    -0.84
     télécharge
    -0.83
     Artist
    -0.81
    搵
    -0.80
    köz
    -0.79
    Tikang
    -0.79
    جعل
    -0.78
    POSITIVE LOGITS
     glowing
    1.67
     glow
    1.43
     emanating
    1.38
     light
    1.31
     shimmer
    1.26
     emitted
    1.21
     surrounded
    1.12
     emitting
    1.10
     floating
    1.09
     sparks
    1.09
    Activations Density 0.014%

    No Known Activations