© 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. 10-GEMMASCOPE-RES-131K
    7. 66429
    Prev
    Next
    INDEX
    Explanations

    pencil sharpener

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

    The neuron strongly activates on occurrences of the word “pencil” (including its various inflections and compounds).

    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
     But
    -2.42
    栳
    -2.28
     merve
    -2.28
     lakini
    -2.14
    IUrlHelper
    -2.13
    ates
    -2.09
     humeur
    -2.06
    琿
    -2.00
    ︕
    -1.98
    锱
    -1.98
    POSITIVE LOGITS
    ではまた
    2.14
    釭
    2.14
    the
    2.13
     It
    2.08
    橚
    1.83
     една
    1.82
    本当
    1.82
     も
    1.81
    сколько
    1.78
     thwart
    1.75
    Activations Density 0.003%

    No Known Activations