© 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. 10-GEMMASCOPE-RES-131K
    7. 66940
    Prev
    Next
    INDEX
    Explanations

    power lines and poles

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

    The neuron responds to technical terms for electrical power‐transmission infrastructure (e.g. insulators, power lines, transmission/distribution components).

    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
     setelah
    -1.30
    ISTOL
    -1.23
    就可以
    -1.23
    Setelah
    -1.19
     selepas
    -1.15
     their
    -1.09
    では
    -1.07
    ↵
    -1.07
    <bos>
    -1.07
     znacznie
    -1.05
    POSITIVE LOGITS
     []:
    1.36
     fences
    1.33
    tifications
    1.20
     gemessen
    1.19
     wires
    1.19
    1.17
    着他
    1.17
    笆
    1.16
     wire
    1.15
    ත්
    1.13
    Activations Density 0.053%

    No Known Activations