© 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. 71565
    Prev
    Next
    INDEX
    Explanations

    am i questions

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

    The neuron activates on occurrences of the first-person “am” (e.g. “I am” or “am I”), especially in “Who am I” or similar constructions.

    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
     a
    -1.77
    زيل
    -1.63
    >
    -1.62
     censi
    -1.58
    intă
    -1.56
     anivers
    -1.54
     complementar
    -1.52
     legislat
    -1.52
    henswürdigkeiten
    -1.52
     couro
    -1.51
    POSITIVE LOGITS
     you
    2.23
    ↵↵
    1.95
    ();
    1.67
    </em>
    1.67
    我们
    1.62
     étu
    1.59
     us
    1.55
    kunjung
    1.54
     száz
    1.50
     polskich
    1.50
    Activations Density 0.021%

    No Known Activations