© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66195
    Prev
    Next
    INDEX
    Explanations

    Board of

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

    The neuron activates specifically on occurrences of the word “Board” referring to a governing or appeals body.

    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
     Then
    -2.25
     communs
    -2.19
     что
    -2.19
     будут
    -2.16
     was
    -2.16
     didnt
    -2.03
    ть
    -2.02
    贔
    -1.99
    </h2>
    -1.97
    vantaged
    -1.96
    POSITIVE LOGITS
    ......”
    2.47
    ଝ
    2.28
    .”
    2.28
    ቼ
    2.23
    趼
    2.22
     andet
    2.20
     bús
    2.17
     pérd
    2.09
     kerusakan
    2.08
     beina
    2.08
    Activations Density 0.008%

    No Known Activations