© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66136
    Prev
    Next
    INDEX
    Explanations

    names and titles

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

    The neuron fires on numeric tokens (digits, including integers and decimals).

    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
    </em>
    -2.55
    </h2>
    -2.02
     $
    -1.88
     […]
    -1.86
     …
    -1.81
    l
    -1.80
    ↵↵
    -1.77
     —
    -1.73
     \&
    -1.69
    an
    -1.66
    POSITIVE LOGITS
     virtue
    2.02
    
    1.93
     semelh
    1.91
    ޏ
    1.90
    倻
    1.88
     Funcion
    1.88
    巂
    1.86
    厹
    1.86
     camiset
    1.85
    卺
    1.85
    Activations Density 0.023%

    No Known Activations