© 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. 93678
    Prev
    Next
    INDEX
    Explanations

    causing to happen

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

    The neuron fires on numeric‐only tokens (i.e. standalone digit sequences).

    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
    Jsp
    -0.74
    Ст
    -0.71
     Harian
    -0.69
    bió
    -0.69
    ktop
    -0.68
    Tecnología
    -0.68
    erschutz
    -0.67
    hound
    -0.67
    Mrs
    -0.67
    یدن
    -0.66
    POSITIVE LOGITS
    させる
    1.05
    させ
    0.94
    させた
    0.93
    させて
    0.91
     lassen
    0.90
     دادن
    0.80
    رارة
    0.79
     thấy
    0.78
    orsa
    0.77
    hedrals
    0.76
    Activations Density 0.042%

    No Known Activations