© 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. 57072
    Prev
    Next
    INDEX
    Explanations

    names starting with Will

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

    The neuron strongly activates on occurrences of the token “Will” (i.e. it detects the substring “Will” in the text).

    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
    vlád
    -0.93
     contributes
    -0.84
     szczegól
    -0.84
     レストラン
    -0.83
     mág
    -0.77
     мере
    -0.77
    füllung
    -0.76
     cultiv
    -0.75
    ix
    -0.75
    Семья
    -0.75
    POSITIVE LOGITS
    owy
    1.43
    liam
    1.42
    fully
    1.27
    ows
    1.07
    ards
    1.04
    helm
    1.02
     be
    0.97
    fulness
    0.97
     wonders
    0.96
    ônica
    0.96
    Activations Density 0.020%

    No Known Activations