© 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. 108314
    Prev
    Next
    INDEX
    Explanations

    check and uncheck

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

    The neuron responds to words and word parts that describe selecting or deselecting items—i.e. tokens related to selection state changes.

    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
     Underground
    -0.75
    vės
    -0.73
     étrangères
    -0.73
    forge
    -0.71
    NOWLEDG
    -0.71
     ().
    -0.71
    Underground
    -0.69
     Giá
    -0.69
    Forge
    -0.68
     sigui
    -0.68
    POSITIVE LOGITS
     des
    3.63
    Des
    2.69
     Des
    2.55
    deselect
    2.50
    des
    2.22
     DES
    2.03
     un
    1.95
    DES
    1.93
     unchecked
    1.67
    un
    1.50
    Activations Density 0.081%

    No Known Activations