© 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. 70085
    Prev
    Next
    INDEX
    Explanations

    names starting with Sai or Say

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

    The neuron fires strongly on any occurrence of the character sequence “Say” (i.e. tokens beginning with the letters S-a-y).

    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
     Cannon
    -0.79
    դ
    -0.78
     Sunrise
    -0.75
    ữ
    -0.73
    garek
    -0.72
    glyph
    -0.70
    öy
    -0.70
    ければ
    -0.69
     Lift
    -0.69
    fokus
    -0.68
    POSITIVE LOGITS
    цією
    0.79
    METHODOLOGY
    0.79
    OLOGICAL
    0.73
    льта
    0.72
     Pomer
    0.70
    メロ
    0.69
     Ál
    0.69
     humer
    0.68
     трансформа
    0.68
    燜
    0.67
    Activations Density 0.023%

    No Known Activations