© 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. 129443
    Prev
    Next
    INDEX
    Explanations

    soothing and soot

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

    The neuron chiefly responds to words that convey a soothing or calming quality.

    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
    örté
    -2.39
    ⚋
    -2.19
     usadas
    -2.14
    ﻦ
    -2.13
    ⤙
    -2.09
    一世
    -2.08
    瀲
    -2.06
    婓
    -2.05
    kipun
    -2.03
    憮
    -2.03
    POSITIVE LOGITS
    ↵
    2.91
     I
    2.73
    AN
    2.58
    *
    2.55
    <i>
    2.52
    –
    2.52
    不管是
    2.47
    不论
    2.45
    要不然
    2.42
    AL
    2.31
    Activations Density 0.003%

    No Known Activations