© 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. 78951
    Prev
    Next
    INDEX
    Explanations

    video controls, looping, publishing

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

    This neuron fires strongly on URL components and related markup (e.g. “http://”, “youtube”, “/watch?”, “=”, “&”) and other technical/code tokens.

    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
    ⋁
    -0.75
     fi
    -0.75
     ALP
    -0.74
     flowered
    -0.74
    悯
    -0.73
     Affirm
    -0.73
    itteet
    -0.72
    mercado
    -0.72
    anza
    -0.71
     Québec
    -0.71
    POSITIVE LOGITS
     controls
    1.02
     auto
    0.93
    controls
    0.84
    vq
    0.84
     loop
    0.82
     Controls
    0.81
    Controls
    0.80
    loop
    0.77
     ramach
    0.76
     frame
    0.75
    Activations Density 0.022%

    No Known Activations