© 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. 34-GEMMASCOPE-RES-131K
    7. 63711
    Prev
    Next
    INDEX
    Explanations

    can followed by understanding or knowledge

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

    The neuron detects occurrences of the phrase “I can,” marking when the speaker asserts their own ability or opinion.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     jugu
    -1.04
     gouverneur
    -0.99
     caballo
    -0.98
    鮰
    -0.98
    ént
    -0.98
    ⎯
    -0.97
     cadeau
    -0.96
    Dichloropropene
    -0.96
    uating
    -0.96
     montant
    -0.96
    POSITIVE LOGITS
     see
    1.97
     only
    1.83
     understand
    1.63
     tell
    1.61
     imagine
    1.49
     say
    1.39
     honestly
    1.37
     assure
    1.35
     now
    1.32
     usually
    1.29
    Activations Density 0.033%

    No Known Activations