© 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. 10-GEMMASCOPE-RES-131K
    7. 104402
    Prev
    Next
    INDEX
    Explanations

    people before verbs or descriptions

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

    The neuron activates on numeric tokens (digits or numbers, including integers and decimals).

    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
     all
    -2.59
     such
    -2.36
     just
    -2.13
     like
    -2.00
     this
    -2.00
    just
    -1.98
     at
    -1.89
     nine
    -1.80
     new
    -1.80
     seems
    -1.77
    POSITIVE LOGITS
    蛲
    2.16
    dengan
    1.85
    蟥
    1.77
    ୬
    1.76
     deliciously
    1.75
     momentous
    1.72
     plafon
    1.70
     วิ
    1.69
     dát
    1.69
     insanely
    1.69
    Activations Density 0.028%

    No Known Activations