© 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. 113182
    Prev
    Next
    INDEX
    Explanations

    numbers like 0.25, 0.5, 0.75

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

    The neuron fires on numeric tokens (especially digits and decimal numbers).

    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
     relying
    -2.02
     They
    -1.95
     singola
    -1.90
     Then
    -1.90
     specifics
    -1.76
     coroa
    -1.70
     gebeten
    -1.67
     связанные
    -1.66
     äusser
    -1.66
     związane
    -1.64
    POSITIVE LOGITS
    vaders
    1.80
    ції
    1.70
    tizers
    1.66
    ᨆ
    1.66
     of
    1.62
     yapa
    1.60
    ciaal
    1.59
     komik
    1.58
    鶲
    1.54
     mikrofon
    1.53
    Activations Density 0.022%

    No Known Activations