© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15566
    Prev
    Next
    INDEX
    Explanations

    you are a

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

    The neuron fires on first‐person self-statements—i.e. clauses where “I” is followed by a verb (am, was, ’m, have, would, do, etc.) indicating the speaker relating personal experience.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    滔
    0.62
    Ranking
    0.60
    ाइवेट
    0.58
     Corporations
    0.57
    看出
    0.56
     Prav
    0.56
    Get
    0.56
    Catch
    0.56
     Popul
    0.55
     Get
    0.54
    POSITIVE LOGITS
     yě
    0.74
     progetto
    0.71
     viaggio
    0.68
     quibusdam
    0.67
    ☺️
    0.67
     esigen
    0.66
     근데
    0.66
     necesarios
    0.65
     版本
    0.65
     首先
    0.63
    Activations Density 0.043%

    No Known Activations