© 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. 10-GEMMASCOPE-RES-131K
    4. 3869
    Prev
    Next
    INDEX
    Explanations

    legal case citations or document headers

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

    The neuron activates on tokens that are numbers (including integers, decimals, dates, docket or case 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_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
    '
    -1.73
     such
    -1.63
    re
    -1.55
     for
    -1.49
     to
    -1.44
    ri
    -1.39
    man
    -1.36
     that
    -1.35
     ゼロ
    -1.34
    釓
    -1.34
    POSITIVE LOGITS
    ⩴
    1.51
    涐
    1.36
     Pemain
    1.32
     Voraussetzung
    1.30
    oiden
    1.30
     несмотря
    1.30
    ätigung
    1.29
    exists
    1.29
    Hozzáférés
    1.27
     Anſ
    1.27
    Activations Density 0.056%

    No Known Activations