© 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. 61408
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    The neuron activates on numeric tokens—especially measurements, distances, and other decimal‐ or digit-based quantities.

    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
     завжди
    -1.78
    ⇴
    -1.68
    🪛
    -1.60
     вважа
    -1.55
     робити
    -1.55
     немає
    -1.52
    焄
    -1.48
     mencegah
    -1.46
     потрібно
    -1.44
     хоче
    -1.43
    POSITIVE LOGITS
     of
    2.14
     —
    1.94
     –
    1.77
    —
    1.76
    \
    1.64
                   
    1.53
    much
    1.53
                
    1.51
     \
    1.48
               
    1.43
    Activations Density 0.022%

    No Known Activations