© 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. 260
    Prev
    Next
    INDEX
    Explanations

    URLs and titles

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

    The neuron activates on standalone numeric tokens (i.e. numbers) in the input.

    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
    зяй
    -0.81
     зависит
    -0.78
    を果た
    -0.76
    From
    -0.75
    edipus
    -0.75
    είς
    -0.75
    With
    -0.74
     lontano
    -0.72
    來源
    -0.71
    Τα
    -0.71
    POSITIVE LOGITS
     this
    1.08
    tobe
    0.93
     aspetti
    0.90
    veri
    0.87
    ivity
    0.86
    ildo
    0.85
     &'
    0.85
    InMillis
    0.84
    masters
    0.84
    maic
    0.82
    Activations Density 0.001%

    No Known Activations