© 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. 34-GEMMASCOPE-RES-131K
    7. 81361
    Prev
    Next
    INDEX
    Explanations

    propagation of waves

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

    The neuron is responding most strongly to tokens that occur very frequently (common words and technical terms) across the scientific text.

    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
    Ingredientes
    -0.75
     raiders
    -0.71
     yum
    -0.71
     formaggio
    -0.69
    consulté
    -0.69
     simpat
    -0.68
    ніше
    -0.67
    ModelState
    -0.67
     Fudge
    -0.67
     résistance
    -0.66
    POSITIVE LOGITS
     propagation
    2.31
     propagating
    2.06
    propagation
    1.77
     propagate
    1.76
    Propagation
    1.64
     propag
    1.64
     Propagation
    1.60
    propag
    1.54
     Propag
    1.43
    Propag
    1.38
    Activations Density 0.068%

    No Known Activations