© 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. 7123
    Prev
    Next
    INDEX
    Explanations

    electrical systems and signals

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

    The neuron activates on occurrences of “electr-” words (e.g. electric, electrical, electronic).

    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
    </b>
    -1.96
    f
    -1.54
    Could
    -1.51
    O
    -1.46
    現状
    -1.46
    i
    -1.45
    Зміст
    -1.44
    できるだけ
    -1.43
    a
    -1.43
    ’
    -1.39
    POSITIVE LOGITS
    </h3>
    1.79
    ୃ
    1.54
    batas
    1.54
    \#:
    1.52
    ではありません
    1.48
    杓
    1.43
    鉝
    1.43
     cuidadosamente
    1.39
    '],
    1.38
     virtuelle
    1.38
    Activations Density 0.094%

    No Known Activations