© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76920
    Prev
    Next
    INDEX
    Explanations

    side by side

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

    The neuron fires on the preposition “by” when it occurs in common multi‐word idioms (e.g. “hard to come by,” “side by side”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     sympathy
    -0.88
    شرة
    -0.76
    pects
    -0.76
     rápidas
    -0.72
    coa
    -0.71
    sekolah
    -0.71
    IBOutlet
    -0.69
    خیص
    -0.69
     rápidos
    -0.69
     to
    -0.68
    POSITIVE LOGITS
     by
    2.22
    by
    1.52
     come
    1.44
    Come
    1.30
    By
    1.27
     Come
    1.20
     BY
    1.18
     By
    1.13
    bys
    1.05
    ByName
    1.03
    Activations Density 0.017%

    No Known Activations