© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9710
    Prev
    Next
    INDEX
    Explanations

    I can, you can

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

    The neuron fires on first‐person, self‐referential statements—especially “I” or “we” plus a modal or action verb expressing ability or desire.

    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
     it
    -1.87
     rendus
    -1.67
     helicópter
    -1.59
     monitores
    -1.55
     guantes
    -1.55
    жется
    -1.51
     regardé
    -1.48
    ⎔
    -1.45
    ющих
    -1.45
     çekilen
    -1.41
    POSITIVE LOGITS
     can
    2.13
     both
    2.09
     with
    2.09
     added
    1.86
     should
    1.76
     more
    1.75
     could
    1.75
     cannot
    1.68
     need
    1.63
    </h2>
    1.61
    Activations Density 0.027%

    No Known Activations