© 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. 81193
    Prev
    Next
    INDEX
    Explanations

    Jack Smith

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

    The neuron primarily detects numeric tokens—especially individual digits or digit sequences used as years, dates, or other numbers.

    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
     safe
    -1.10
    safe
    -0.91
     safer
    -0.88
    安全性
    -0.86
     safely
    -0.82
     Waffle
    -0.81
     Feld
    -0.81
    安全的
    -0.80
    Veu
    -0.79
    fondo
    -0.78
    POSITIVE LOGITS
     Ripper
    1.43
    London
    1.21
     London
    1.13
    Jack
    1.09
     Jack
    1.02
     Victorian
    1.01
    Ri
    0.92
     suspects
    0.92
     Thames
    0.90
    Victorian
    0.88
    Activations Density 0.008%

    No Known Activations