© 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. 3733
    Prev
    Next
    INDEX
    Explanations

    items joined by and

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

    This neuron detects numeric tokens (especially multi‐digit numbers like reference or section identifiers).

    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
     étan
    -1.44
     ngayon
    -1.40
    Now
    -1.37
    othes
    -1.37
     vė
    -1.30
     selera
    -1.30
    raught
    -1.30
     etc
    -1.28
     первом
    -1.27
     médic
    -1.25
    POSITIVE LOGITS
     when
    1.37
     เมื่อ
    1.32
     этих
    1.27
    しまい
    1.27
     也
    1.27
     once
    1.26
    when
    1.25
     אף
    1.23
     to
    1.23
    which
    1.22
    Activations Density 0.064%

    No Known Activations