© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73649
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron responds to numeric literals—especially multi‐digit numbers such as years, dates, version 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
     sabias
    -1.88
     dokumenti
    -1.77
     impresionantes
    -1.73
     being
    -1.71
     моего
    -1.63
     maravillosas
    -1.59
    Ꮞ
    -1.57
     espectaculares
    -1.55
     hermosas
    -1.54
     людини
    -1.53
    POSITIVE LOGITS
     with
    2.33
    enchymal
    1.80
     vloer
    1.77
    ']))
    
    1.75
     также
    1.70
    </i>
    1.69
    <bos>
    1.61
     provide
    1.60
     mondeo
    1.59
    ];
    
    1.58
    Activations Density 0.137%

    No Known Activations