© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84902
    Prev
    Next
    INDEX
    Explanations

    reluctant to, relentless

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

    The main thing this neuron does is find words and phrases expressing reluctance or unwillingness.

    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
    葙
    -2.95
    鐃
    -2.75
    荭
    -2.70
    菝
    -2.63
    Ꮞ
    -2.53
    谖
    -2.39
    剮
    -2.33
    賔
    -2.31
                        
    -2.27
    嵙
    -2.20
    POSITIVE LOGITS
    ’
    2.95
     he
    2.56
    .
    2.47
    "
    2.30
    を始め
    2.25
     
    2.19
    \
    2.14
    ?"
    2.11
    0
    2.09
     Would
    2.05
    Activations Density 0.007%

    No Known Activations