© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20079
    Prev
    Next
    INDEX
    Explanations

    for

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

    The main thing this neuron does is detect numeric tokens (including integers and decimals) in the 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
        
    -1.86
    ]
    -1.65
     
    -1.62
    }
    -1.59
    </td>
    -1.59
    utiliser
    -1.55
    k
    -1.55
    especially
    -1.51
    ⏑
    -1.50
    i
    -1.46
    POSITIVE LOGITS
     you
    2.66
     it
    1.88
     człowiek
    1.84
     dôle
    1.62
     cesty
    1.59
    ITARY
    1.55
    ير
    1.51
    ໊
    1.47
     voľ
    1.45
     kwiet
    1.45
    Activations Density 0.066%

    No Known Activations