© 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. 1477
    Prev
    Next
    INDEX
    Explanations

    sparse representations

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

    The neuron fires strongly on technical terms around “sparse representations” (and related jargon) in scientific paper 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
     drowning
    -0.75
    ocha
    -0.75
    тины
    -0.70
     Crystal
    -0.70
     monté
    -0.69
    Crystal
    -0.69
    Survey
    -0.68
     Personality
    -0.68
     survives
    -0.67
     kolem
    -0.67
    POSITIVE LOGITS
     sparse
    1.59
     spars
    1.55
     dictionary
    1.54
    dictionary
    1.31
    sparse
    1.20
    Sparse
    1.16
     Sparse
    1.16
    字典
    1.13
    Dictionary
    1.10
     Dictionary
    1.08
    Activations Density 0.031%

    No Known Activations