© 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. 73503
    Prev
    Next
    INDEX
    Explanations

    Laurie, Lori, and Deloitte

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

    The main thing this neuron does is find numeric values (including integers and decimal numbers).

    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
     jezt
    -3.13
    絎
    -3.08
    es
    -2.84
     dieß
    -2.75
    t
    -2.69
     nothwendig
    -2.53
    
    -2.48
     gekenn
    -2.45
    という
    -2.39
    說
    -2.39
    POSITIVE LOGITS
    籥
    2.67
    塤
    2.55
    镔
    2.53
     Also
    2.52
    ſelves
    2.45
     また
    2.36
    瓩
    2.27
     nasıl
    2.27
    詒
    2.25
    ᨁ
    2.22
    Activations Density 0.008%

    No Known Activations