© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10178
    Prev
    Next
    INDEX
    Explanations

    im glad we

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

    The neuron fires on words used in self-referential, first-person statements expressing the speaker’s own experience or perspective.

    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_31_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
     TikTok
    1.09
    TikTok
    1.09
    ChatGPT
    1.06
    ‒
    1.04
     PFAS
    0.93
     ২০২২
    0.92
     ২০২৩
    0.88
     проє
    0.88
    utiérrez
    0.87
    ˗
    0.86
    POSITIVE LOGITS
    ってる
    1.31
     atleast
    1.30
     aswell
    1.24
     piu
    1.22
     সাধারন
    1.19
     isnt
    1.16
     upto
    1.16
     alot
    1.13
     kinda
    1.10
     انها
    1.09
    Activations Density 0.097%

    No Known Activations