© 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. 34-GEMMASCOPE-RES-131K
    7. 1830
    Prev
    Next
    INDEX
    Explanations

    special characters or phrases

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

    The neuron responds to tokens containing numbers (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
     स्था
    -0.76
    净化
    -0.71
    žite
    -0.71
     vitesse
    -0.68
     Ausland
    -0.67
     Mitgliedern
    -0.65
    Sursa
    -0.65
    oids
    -0.65
     מט
    -0.64
    ui
    -0.64
    POSITIVE LOGITS
    兴趣
    0.73
    bcd
    0.72
    Parent
    0.71
    园
    0.68
    tidal
    0.65
    Nib
    0.65
     Kaf
    0.64
     утра
    0.64
    mobi
    0.64
    UTC
    0.63
    Activations Density 0.080%

    No Known Activations