© 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. 73624
    Prev
    Next
    INDEX
    Explanations

    website URLs and tags

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

    The neuron responds to numeric tokens—i.e. sequences of digits.

    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
     previously
    -0.90
     directors
    -0.88
     probably
    -0.86
     Roots
    -0.85
     three
    -0.85
     two
    -0.85
     where
    -0.83
     surprisingly
    -0.82
     весна
    -0.82
     Pfund
    -0.82
    POSITIVE LOGITS
     visitor
    0.97
    リアン
    0.97
     katholischen
    0.93
     artigo
    0.93
     Ähnliche
    0.91
     stejně
    0.91
    ೭
    0.91
    timg
    0.90
     DMCA
    0.89
     инженер
    0.89
    Activations Density 0.011%

    No Known Activations