© 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. 1751
    Prev
    Next
    INDEX
    Explanations

    graph and network structures

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

    The neuron strongly activates on technical, math‐oriented terms (e.g. “similarity,” “matrix,” “structure,” “data,” “compute,” “scale”) typical of scientific or algorithmic descriptions.

    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
    setLayoutManager
    -0.78
     derin
    -0.74
    anas
    -0.74
    issão
    -0.73
    ents
    -0.73
    zyny
    -0.71
    groep
    -0.71
     holo
    -0.68
     δη
    -0.66
    iness
    -0.65
    POSITIVE LOGITS
     matrix
    1.51
     матри
    1.30
    matrix
    1.23
     matrices
    1.20
    Matrix
    1.19
     adjacency
    1.17
    矩阵
    1.13
     Matrix
    1.12
     symmetric
    1.09
     sym
    1.03
    Activations Density 0.016%

    No Known Activations