© 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. 110624
    Prev
    Next
    INDEX
    Explanations

    the followed by specific noun

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

    The neuron activates on numeric tokens (especially decimal or other number values).

    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
     that
    -2.80
    </h2>
    -2.20
     with
    -1.73
    頂きました
    -1.70
     vehemently
    -1.70
     Perhaps
    -1.64
     if
    -1.63
     slight
    -1.60
    頂いた
    -1.59
     When
    -1.59
    POSITIVE LOGITS
     territo
    1.70
     GRATU
    1.69
    又被
    1.59
     !!!!
    1.58
     amazing
    1.56
     alip
    1.56
    把她
    1.50
    plication
    1.50
    kinda
    1.47
     wonderful
    1.45
    Activations Density 0.082%

    No Known Activations