© 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. 99043
    Prev
    Next
    INDEX
    Explanations

    well followed by names or technical terms

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

    The neuron is highly activated by the standalone token “Well” (in any context where “Well” appears as its own word).

    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
     well
    -1.71
    età
    -1.15
    郄
    -1.13
    蝙
    -1.08
     bien
    -1.05
     gerai
    -1.00
     性感
    -0.99
    feliz
    -0.98
     tortura
    -0.98
     hyvin
    -0.96
    POSITIVE LOGITS
    known
    1.28
    ington
    1.26
     versed
    1.19
    defined
    1.13
    rounded
    1.06
    sin
    1.05
    come
    1.04
    ضای
    1.02
    中國
    0.98
    It
    0.97
    Activations Density 0.046%

    No Known Activations