© 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. 112450
    Prev
    Next
    INDEX
    Explanations

    assuming variable conditions

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

    The neuron fires on the word “assuming,” flagging when an explicit assumption is stated.

    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
     utiliser
    -2.19
    
    -1.96
     imprimer
    -1.95
    ⚣
    -1.95
    惊艳
    -1.95
    ᯾
    -1.94
    淠
    -1.94
    
    -1.91
    蟶
    -1.90
    蛲
    -1.86
    POSITIVE LOGITS
    k
    2.16
    t
    2.05
     when
    2.02
     both
    2.02
     by
    2.02
     for
    1.98
    u
    1.96
    n
    1.95
     with
    1.93
     where
    1.93
    Activations Density 0.007%

    No Known Activations