© 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. 34-GEMMASCOPE-RES-131K
    7. 60767
    Prev
    Next
    INDEX
    Explanations

    number 5

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

    The neuron activates on numeric tokens (multi‐digit 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
     presa
    -0.88
     commencent
    -0.86
    FRA
    -0.81
    ницу
    -0.80
    ↄ
    -0.79
    hello
    -0.78
     pounds
    -0.78
    ął
    -0.78
     voulu
    -0.77
     appartiennent
    -0.77
    POSITIVE LOGITS
    Celebrity
    0.85
     дев
    0.82
    Jays
    0.75
     igång
    0.75
    gress
    0.74
     Rogers
    0.73
     meest
    0.73
    Wein
    0.73
    Scalar
    0.73
    eig
    0.73
    Activations Density 0.045%

    No Known Activations