© 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. 98275
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    This neuron detects the numeric and abbreviated reporter‐citation components (volume numbers, reporter initials, page numbers, etc.) in legal case citations.

    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
    ᾽
    -1.04
     Deccan
    -1.03
     harap
    -0.98
     Shropshire
    -0.98
     FEW
    -0.96
    她就
    -0.96
    T
    -0.96
     INDIVIDUAL
    -0.95
    pread
    -0.93
     setUser
    -0.93
    POSITIVE LOGITS
    Carolina
    1.05
    CMAKE
    1.03
    ”،
    1.00
    LikeLike
    0.99
    aspectj
    0.98
    اريخ
    0.95
    anoia
    0.95
    רו
    0.95
     فرص
    0.95
     one
    0.93
    Activations Density 0.016%

    No Known Activations