© 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. 10581
    Prev
    Next
    INDEX
    Explanations

    interrogate the reasons

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

    The neuron activates on any occurrence of the root “interrog,” i.e. words like interrogate, interrogation, interrogated, etc.

    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
     estímulo
    -2.56
    其他的
    -2.47
     levit
    -2.39
    鲠
    -2.39
     brauche
    -2.28
    ி
    -2.28
     résistant
    -2.27
    attutto
    -2.27
    𔘓
    -2.23
    indest
    -2.22
    POSITIVE LOGITS
    狆
    2.78
    但却
    2.66
    涐
    2.44
     verbess
    2.36
    0
    2.34
    
    2.34
    Поэтому
    2.33
    ჻
    2.31
    他会
    2.27
    because
    2.22
    Activations Density 0.002%

    No Known Activations