© 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. 10-GEMMASCOPE-RES-131K
    7. 40738
    Prev
    Next
    INDEX
    Explanations

    HHV-6 reactivation

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

    numbers in scientific or technical contexts, particularly gene identifiers like p16 or numeric values like 6.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on standalone numeric tokens—most strongly on the digit “6.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    <i>
    -1.68
     augusti
    -1.54
     istan
    -1.44
     erat
    -1.41
    <b>
    -1.38
    the
    -1.37
    bi
    -1.34
    V
    -1.34
    とした
    -1.33
    O
    -1.32
    POSITIVE LOGITS
     vuestra
    1.77
     manej
    1.65
     recomendamos
    1.50
     preguntar
    1.48
     fruitless
    1.41
    噚
    1.39
    งิน
    1.38
     divertidos
    1.37
     difund
    1.37
     canciones
    1.36
    Activations Density 0.042%

    No Known Activations