© 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. 109389
    Prev
    Next
    INDEX
    Explanations

    numbers starting with 4

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

    The neuron activates on multi‐digit numeric tokens (e.g. years, phone numbers, or other standalone number sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    sequences of digits that form phone numbers or numeric codes.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    numeric digit sequences, especially multi‑digit numbers appearing in URLs, ports, phone numbers, dates, or addresses.

    oai_token-act-pair · gpt-5Triggered 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
     preto
    -1.05
     brisa
    -1.03
     both
    -0.94
     Psic
    -0.94
    𝗀
    -0.90
     profesora
    -0.88
    او
    -0.88
     very
    -0.88
     koment
    -0.88
    пат
    -0.87
    POSITIVE LOGITS
     Magnum
    0.94
    est
    0.91
     permettent
    0.88
     solidif
    0.85
     solução
    0.84
    などを
    0.84
     detenidos
    0.84
     كامل
    0.82
    fiant
    0.81
    実現
    0.81
    Activations Density 0.020%

    No Known Activations