© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 499
    Prev
    Next
    INDEX
    Explanations

    food or ingredient

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

    physical objects and actions related to manipulating, assembling, or using mechanical or technical components.

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

    This neuron detects numeric tokens (digits, quantities, and measurements) in the text.

    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
     or
    -3.64
     your
    -2.56
     или
    -2.41
     either
    -2.14
    或者
    -2.03
     if
    -2.00
     либо
    -1.98
    或
    -1.89
     hoặc
    -1.84
     bordados
    -1.77
    POSITIVE LOGITS
     to
    1.71
     yesterday
    1.65
     because
    1.58
     чтобы
    1.55
     myself
    1.47
     since
    1.41
     क्योंकि
    1.41
     ontem
    1.41
     pensando
    1.41
     eftersom
    1.40
    Activations Density 0.177%

    No Known Activations