© 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. 108995
    Prev
    Next
    INDEX
    Explanations

    be attributed

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

    The neuron strongly activates on very common auxiliary and linking verbs (forms of “to be”) and modal verbs.

    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
    TERA
    -0.77
     emosi
    -0.73
    SERIAL
    -0.73
    lesque
    -0.73
     proche
    -0.71
    ystemen
    -0.70
    ciptakan
    -0.69
    SFER
    -0.69
    boon
    -0.69
    pires
    -0.68
    POSITIVE LOGITS
     attributed
    5.94
     attribute
    4.84
    attributed
    4.31
     attribution
    4.00
     atribu
    3.89
     attributes
    3.77
     Attribute
    3.66
    attribute
    3.64
     attributable
    3.53
     attribu
    3.50
    Activations Density 0.119%

    No Known Activations