© 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. 75655
    Prev
    Next
    INDEX
    Explanations

    gentle

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

    The neuron fires on occurrences of the word “gentle” (and its inflected forms like “gently”).

    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
     dimly
    -0.88
     だっ
    -0.88
    比如说
    -0.85
    ایی
    -0.84
    🚉
    -0.82
    我先
    -0.82
    quisar
    -0.81
     Cheer
    -0.80
     bandoulière
    -0.80
     chilli
    -0.77
    POSITIVE LOGITS
     slope
    1.36
    slope
    1.23
     reminder
    1.22
     slopes
    1.20
     reminders
    1.14
     gently
    1.13
     giants
    1.12
     yet
    1.09
     Reminder
    1.07
     but
    1.06
    Activations Density 0.011%

    No Known Activations