© 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. 34-GEMMASCOPE-RES-131K
    7. 31490
    Prev
    Next
    INDEX
    Explanations

    numbers containing 2

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

    the neuron activates on tokens that are numeric—i.e. digit sequences or 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_34/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
     like
    -0.92
    hoku
    -0.90
     histórico
    -0.90
    ggars
    -0.85
    !="")
    -0.84
     inicio
    -0.84
    RENDER
    -0.83
    transporter
    -0.83
     incorporar
    -0.83
    tvar
    -0.83
    POSITIVE LOGITS
    nd
    1.08
     își
    0.91
    న్న
    0.88
     входят
    0.85
    2
    0.79
    ólicas
    0.78
    Gerd
    0.77
     lastly
    0.77
     worin
    0.76
    chromatic
    0.75
    Activations Density 0.013%

    No Known Activations