© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107331
    Prev
    Next
    INDEX
    Explanations

    media titles and names

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

    The neuron fires specifically on the surname “Wilson.”

    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
    Several
    -0.94
    sth
    -0.87
    kritik
    -0.87
    lık
    -0.86
    ெ
    -0.85
    delige
    -0.85
    Rumors
    -0.82
    AMOUNT
    -0.81
     Conclu
    -0.81
    AFTA
    -0.81
    POSITIVE LOGITS
    埼
    0.88
     ahora
    0.88
    exif
    0.86
    話す
    0.79
    大半
    0.79
    medskip
    0.79
     Luego
    0.79
    usal
    0.79
    を経
    0.77
     noté
    0.76
    Activations Density 0.000%

    No Known Activations