© 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. 39629
    Prev
    Next
    INDEX
    Explanations

    oxidative, guys, females, infant

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

    This neuron detects commas followed by "and" that serve as conjunctions in lists or compound sentences.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron primarily activates on numeric tokens (i.e. standalone numbers or numeric sequences).

    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
     for
    -1.22
     this
    -1.19
     by
    -1.10
    N
    -1.07
     if
    -1.02
     from
    -1.02
    X
    -1.01
     rozwiąz
    -0.92
     zależ
    -0.92
     four
    -0.90
    POSITIVE LOGITS
     twa
    1.09
     ail
    1.09
    作战
    1.05
    PASO
    1.00
    ครื่อง
    1.00
    Ꮐ
    0.98
    争议
    0.98
     ons
    0.98
     pratiquer
    0.97
    Kontra
    0.96
    Activations Density 0.248%

    No Known Activations