© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4952
    Prev
    Next
    INDEX
    Explanations

    .

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

    The neuron fires on self-referential AI ownership statements—especially first-person “I” and model identity/disclaimer phrases (e.g. “As a large language model, I do not have subjective 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
     &
    0.70
     Уже
    0.65
     già
    0.64
     Ambassador
    0.61
     Inspired
    0.61
     @
    0.60
     signé
    0.58
     +
    0.57
     Signature
    0.57
     സ്വന്ത
    0.57
    POSITIVE LOGITS
     일반적으로
    0.81
    𒐪
    0.79
     diferentes
    0.79
     algunas
    0.75
     classifications
    0.74
    adecimal
    0.74
     다음과
    0.73
     genellikle
    0.73
     verschillende
    0.73
     forskellige
    0.73
    Activations Density 0.218%

    No Known Activations