© 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. 22-GEMMASCOPE-RES-131K
    7. 15937
    Prev
    Next
    INDEX
    Explanations

    assume a supposition

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

    The neuron fires strongly on occurrences of the verb “assume.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     '
    -3.52
    でも
    -3.13
    3
    -2.75
    )
    -2.67
    !"
    -2.67
    のは
    -2.55
     resounding
    -2.52
     alcuni
    -2.47
    }\
    -2.41
    9
    -2.39
    POSITIVE LOGITS
     that
    2.92
    
    2.33
    ⬮
    2.31
    涐
    2.16
    喼
    2.14
    鱘
    2.13
    Ꮵ
    2.06
     碗
    2.05
    ⸒
    2.00
    gulation
    1.98
    Activations Density 0.012%

    No Known Activations