© 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. 1437
    Prev
    Next
    INDEX
    Explanations

    years and publication details

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

    The neuron is selectively detecting numeric tokens—especially multi-digit numbers like years, volume/issue/page numbers, and other reference identifiers in citations.

    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
    Twenty
    -0.94
    Forty
    -0.88
    Thirty
    -0.86
     Thirty
    -0.85
     Twenty
    -0.85
    Fifty
    -0.85
     Forty
    -0.84
     fifty
    -0.82
     Fifty
    -0.82
     eighty
    -0.82
    POSITIVE LOGITS
     five
    0.80
    umenten
    0.79
     ask
    0.79
    洀
    0.78
     Tiss
    0.78
    نائ
    0.77
    ask
    0.76
     scaler
    0.76
    stalgia
    0.75
    ça
    0.75
    Activations Density 0.022%

    No Known Activations