© 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. 12962
    Prev
    Next
    INDEX
    Explanations

    turned away or down

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

    The neuron activates on verbs (and verb phrases) that express refusal or rejection (e.g. “turned down,” “turned away,” “spurning”).

    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
    -1.93
     and
    -1.85
     justin
    -1.77
     spurred
    -1.70
    ？！
    -1.68
     tilby
    -1.64
     пев
    -1.63
    ter
    -1.62
     अनुसार
    -1.62
    سيم
    -1.61
    POSITIVE LOGITS
    蕺
    2.45
    鸶
    2.39
    ⬈
    2.28
    籴
    2.23
    ౭
    2.19
    脔
    2.17
    ization
    2.11
    ᯾
    2.09
     пять
    2.06
    腘
    2.06
    Activations Density 0.003%

    No Known Activations