© 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. 111814
    Prev
    Next
    INDEX
    Explanations

    degree of

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

    This neuron detects numerical measurements, especially standalone numbers and “degree(s)” expressions.

    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
    
    -2.08
     nastro
    -2.08
    ՚
    -2.05
    栳
    -2.03
    
    -2.00
    铩
    -1.95
     generado
    -1.91
    =“
    -1.90
    琲
    -1.89
     ruines
    -1.88
    POSITIVE LOGITS
    2
    2.56
    ’
    2.22
     of
    2.17
    A
    2.14
     hochwertige
    2.08
    </sup>
    1.99
    3
    1.98
    This
    1.98
    If
    1.97
    ">
    1.95
    Activations Density 0.016%

    No Known Activations