© 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. 11023
    Prev
    Next
    INDEX
    Explanations

    Photo credit names

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

    The neuron activates on numeric tokens (integers or decimals), i.e. on numbers in the text.

    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
    ں
    -1.72
     teus
    -1.70
    鋮
    -1.62
    ’，
    -1.53
     parachoque
    -1.53
     mereka
    -1.48
    𝘙
    -1.45
    q
    -1.44
     jardin
    -1.43
    ugier
    -1.43
    POSITIVE LOGITS
     ignite
    1.90
     wichtigen
    1.83
    would
    1.83
     besonderen
    1.63
    must
    1.60
    ться
    1.56
     embark
    1.56
     会
    1.55
    。】
    1.53
    いただける
    1.52
    Activations Density 0.013%

    No Known Activations