© 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. 10-GEMMASCOPE-RES-131K
    7. 13132
    Prev
    Next
    INDEX
    Explanations

    tone, sound, or emotional quality

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

    The neuron activates on occurrences of the word “tone.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    s
    -3.39
    ?”
    -3.03
     Like
    -3.03
    >
    -2.98
     Somehow
    -2.97
     Obviously
    -2.64
     Historically
    -2.53
     Both
    -2.52
     Completely
    -2.50
    Ꮵ
    -2.50
    POSITIVE LOGITS
    玏
    2.80
    ꔹ
    2.66
    𓐍
    2.63
    癰
    2.61
    骉
    2.50
    翃
    2.48
    ſſen
    2.45
    櫪
    2.38
    鍆
    2.36
    ￬
    2.34
    Activations Density 0.003%

    No Known Activations