© 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. 473
    Prev
    Next
    INDEX
    Explanations

    logical operator or

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

    The neuron fires on the coordinating conjunction “or.”

    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
    <bos>
    -1.86
     capitán
    -1.15
    Ikus
    -1.10
    nữ
    -1.09
     ideen
    -1.09
     cadeiras
    -1.07
    fotograf
    -1.07
    Açık
    -1.05
     Abp
    -1.04
    慟
    -1.02
    POSITIVE LOGITS
     if
    1.51
     cuya
    1.13
    為に
    1.10
    么
    1.08
    larımız
    1.04
     from
    1.01
    事が
    0.99
     valoraciones
    0.99
    ("./
    0.98
     gleaming
    0.98
    Activations Density 0.039%

    No Known Activations