© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40306
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

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

    The neuron selectively activates on individual digit tokens (0–9) in numeric data, i.e. it’s detecting numbers.

    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
    がありますが
    -1.38
    Хотя
    -1.34
    Конечно
    -1.24
    も
    -1.23
    Karakteristik
    -1.22
    は
    -1.18
    <bos>
    -1.17
     енер
    -1.16
     Usaha
    -1.14
    があります
    -1.13
    POSITIVE LOGITS
    為に
    1.54
    だけではなく
    1.38
    久し
    1.35
     situés
    1.31
     sujetos
    1.26
    に入れる
    1.24
    ();
    
    1.21
    あー
    1.20
    '));
    1.20
     biet
    1.20
    Activations Density 0.026%

    No Known Activations