© 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. 65836
    Prev
    Next
    INDEX
    Explanations

    futile, futility, pointless

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

    The neuron fires strongly on words conveying futility or pointlessness (e.g., “futile,” “pointless”).

    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
    Erreferent
    -3.06
    
    -2.83
    蟊
    -2.83
    龃
    -2.81
    茘
    -2.77
     occur
    -2.67
    嗫
    -2.66
     iſt
    -2.64
    狆
    -2.63
    ActionCreators
    -2.61
    POSITIVE LOGITS
    )
    2.91
            
    2.78
     letzten
    2.75
    ли
    2.70
    –
    2.61
     یک
    2.56
     Does
    2.45
    ти
    2.44
     использование
    2.42
    僱
    2.42
    Activations Density 0.003%

    No Known Activations