© 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. 78804
    Prev
    Next
    INDEX
    Explanations

    RIY words

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

    The neuron activates strongly on numeric literals (sequence of digits) in code.

    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
     kebakaran
    -0.79
     inds
    -0.77
    ofing
    -0.75
     Remastered
    -0.73
    льзя
    -0.72
    ͞
    -0.71
     frito
    -0.70
    atung
    -0.69
     tassel
    -0.69
    sendFile
    -0.69
    POSITIVE LOGITS
     opak
    1.02
     Під
    0.89
    (()
    0.86
     []);
    0.84
     aguja
    0.81
     individuell
    0.79
     llaves
    0.78
    機關
    0.77
    sial
    0.77
     muñeca
    0.77
    Activations Density 0.059%

    No Known Activations