© 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. 100942
    Prev
    Next
    INDEX
    Explanations

    accidental actions and consequences

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

    The neuron fires on occurrences of the adverb “accidentally,” flagging mentions of unintended or accidental actions.

    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
    o
    -2.28
    D
    -2.05
     But
    -2.05
    S
    -2.00
    of
    -1.91
    м
    -1.89
    J
    -1.82
    E
    -1.80
    ه
    -1.79
    C
    -1.77
    POSITIVE LOGITS
    闼
    2.19
    蘩
    2.16
    囖
    1.95
    ciutto
    1.94
     Inſ
    1.91
    其妙
    1.89
    とその
    1.89
    をご紹介
    1.87
    坶
    1.87
    नलोड
    1.80
    Activations Density 0.003%

    No Known Activations