© 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. 54191
    Prev
    Next
    INDEX
    Explanations

    television performances

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

    The neuron detects numeric tokens (i.e. number literals) 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
    繚
    -0.69
     Paco
    -0.68
    Gathering
    -0.68
     Moha
    -0.67
    在线
    -0.67
     NORMAN
    -0.66
    SEARCH
    -0.66
     bst
    -0.64
    ciclopedia
    -0.63
     frappe
    -0.63
    POSITIVE LOGITS
    aggregate
    0.69
    reducible
    0.68
    droj
    0.67
    thun
    0.67
    ίζ
    0.66
    jalan
    0.66
     gestational
    0.66
    ✷
    0.65
     Ministries
    0.65
    QI
    0.65
    Activations Density 0.053%

    No Known Activations