© 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. 64749
    Prev
    Next
    INDEX
    Explanations

    Stim, stimulate, stimulation

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

    The neuron activates for word beginnings like "stim" that appear in scientific or technical terms such as "stimulus," "stimulation," or "stimuli."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     civile
    -0.81
     bucks
    -0.77
     troubles
    -0.76
    floors
    -0.75
    état
    -0.75
    clientID
    -0.74
    bursts
    -0.73
     Coronation
    -0.72
     fince
    -0.72
    flakes
    -0.72
    POSITIVE LOGITS
     Stim
    1.27
     Сти
    1.20
     Sti
    1.15
    stim
    1.09
    Sti
    1.09
     sti
    1.06
    Stir
    1.06
     Stir
    1.03
     stimulate
    1.02
    Stim
    1.02
    Activations Density 0.030%

    No Known Activations