© 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. 34-GEMMASCOPE-RES-131K
    7. 76762
    Prev
    Next
    INDEX
    Explanations

    ordinal rankings

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

    The neuron is triggered by numeric tokens—especially standalone numbers or numeric statistics (ranks, scores, measurements) 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_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
     более
    -0.86
    ⽼
    -0.86
     dislike
    -0.84
    卺
    -0.84
     \%$\\
    -0.84
     Zwei
    -0.82
    NANCY
    -0.81
    ürm
    -0.81
    श्चित
    -0.80
    onResume
    -0.79
    POSITIVE LOGITS
     second
    2.38
     third
    2.31
     fourth
    2.05
     fifth
    1.96
     sixth
    1.87
     in
    1.80
     seventh
    1.72
     first
    1.66
    third
    1.55
     eighth
    1.52
    Activations Density 0.032%

    No Known Activations