© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66931
    Prev
    Next
    INDEX
    Explanations

    copyright and author information

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

    This neuron detects standalone numeric tokens (sequences of digits) such as version numbers, years, line numbers, etc.

    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
    a
    -3.02
    P
    -2.88
    S
    -2.70
    '
    -2.70
    F
    -2.59
    3
    -2.47
    L
    -2.42
     Then
    -2.39
    "
    -2.36
    B
    -2.34
    POSITIVE LOGITS
    replyreport
    2.81
    ৄ
    2.63
    艽
    2.61
    ㉕
    2.61
    眚
    2.55
    ㉗
    2.53
    
    2.50
     mundos
    2.45
     แต่
    2.41
    垕
    2.34
    Activations Density 0.095%

    No Known Activations