© 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. 22-GEMMASCOPE-RES-131K
    7. 71252
    Prev
    Next
    INDEX
    Explanations

    solar energy, psychoanalytic, alcohol behavior

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

    This neuron is selectively activated by numeric tokens (digits and numbers) 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_22/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
    沵
    -1.33
     perpé
    -1.31
     Whilst
    -1.30
     bola
    -1.24
     hatta
    -1.23
    珦
    -1.23
    ❓
    -1.21
     bawat
    -1.20
    (^_^
    -1.20
     Nigeria
    -1.20
    POSITIVE LOGITS
    paravant
    1.23
    だが
    1.23
    imbur
    1.21
     anstatt
    1.14
     zamiast
    1.13
    ָּ
    1.12
    进去
    1.09
    єдна
    1.09
    ַּ
    1.08
     geluid
    1.05
    Activations Density 0.008%

    No Known Activations