© 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. 79103
    Prev
    Next
    INDEX
    Explanations

    legal disclaimer phrases

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

    The neuron activates on tokens containing numeric characters, i.e. it identifies numbers or digit sequences 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
     since
    -1.34
     like
    -1.08
     поскольку
    -0.88
     uint
    -0.86
    以来
    -0.84
     Since
    -0.80
    مثل
    -0.80
     seit
    -0.78
    Since
    -0.77
    since
    -0.75
    POSITIVE LOGITS
    FIGURE
    1.47
     FIGURE
    1.39
    see
    0.96
    SEE
    0.83
     přid
    0.77
    Figure
    0.75
     see
    0.75
    不出
    0.75
     Figure
    0.75
    Caution
    0.74
    Activations Density 0.018%

    No Known Activations