© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64640
    Prev
    Next
    INDEX
    Explanations

    im Deutschen or in the

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

    The neuron is a high‐reactor for very common short function words and contractions (e.g. “in,” “ins,” “im,” “the,” “des,” “vom”).

    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
    などの
    -0.83
    WEDNESDAY
    -0.82
     encontrados
    -0.82
    ांस
    -0.81
     in
    -0.80
    kwür
    -0.80
    紡
    -0.80
     место
    -0.78
     plek
    -0.78
    への
    -0.77
    POSITIVE LOGITS
    itiert
    1.24
     Cockpit
    1.02
    itieren
    0.99
     meantime
    0.98
     Then
    0.94
    دارة
    0.92
     limbo
    0.86
    fluidic
    0.86
    際に
    0.86
    PET
    0.86
    Activations Density 0.013%

    No Known Activations