© 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. 128075
    Prev
    Next
    INDEX
    Explanations

    PS followed by identifier

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

    The neuron selectively fires on standalone numeric tokens (integer literals) in code or 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_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
    ৄ
    -2.20
    
    -2.06
    潆
    -1.98
    ࿙
    -1.97
    ementara
    -1.92
    ࿊
    -1.85
    ⩤
    -1.73
    鉕
    -1.72
     sientes
    -1.67
    不着
    -1.66
    POSITIVE LOGITS
    '
    2.45
    u
    2.31
    that
    2.14
    A
    2.09
     dasarnya
    2.02
    да
    1.88
    </i>
    1.88
    ar
    1.86
     многие
    1.84
    a
    1.84
    Activations Density 0.008%

    No Known Activations