© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77927
    Prev
    Next
    INDEX
    Explanations

    sequential word combinations

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

    The neuron fires on the boilerplate license header lines (comment markers, stars, copyright notice, “Licensed under the Apache License, Version 2.0,” etc.) at the top of source files.

    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
    맑
    -0.80
     eclips
    -0.77
     axial
    -0.75
    哪儿
    -0.75
     spills
    -0.75
    waż
    -0.74
    Hm
    -0.74
    牺牲
    -0.73
     detonation
    -0.73
     Privy
    -0.71
    POSITIVE LOGITS
    usitis
    0.75
    grpc
    0.75
    aniem
    0.74
    肺
    0.74
     gange
    0.73
     насе
    0.72
    zookeeper
    0.71
     validity
    0.71
    بر
    0.71
    tische
    0.70
    Activations Density 0.017%

    No Known Activations