© 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. 22-GEMMASCOPE-RES-131K
    7. 38308
    Prev
    Next
    INDEX
    Explanations

    Q, R, 1, white, Hungary, Joseph

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

    The neuron fires on numeric tokens (multi‐digit 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_22/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
     breiten
    -0.87
     both
    -0.85
     feasting
    -0.83
     полноцен
    -0.82
    seri
    -0.82
    koc
    -0.79
    出色
    -0.79
    봐
    -0.78
    בין
    -0.77
     optimieren
    -0.77
    POSITIVE LOGITS
    homology
    0.93
    Dichlorobenzene
    0.92
    СС
    0.85
    jukan
    0.85
    ⋃
    0.85
    nicas
    0.85
    ࿚
    0.84
    嘉
    0.84
    ença
    0.83
     llorar
    0.83
    Activations Density 0.010%

    No Known Activations