© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10822
    Prev
    Next
    INDEX
    Explanations

    crisis support numbers

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

    The neuron consistently activates on boilerplate blog or webpage metadata elements—things like “Bookmark the permalink,” “posted in,” “Translation,” and other site‐template tokens.

    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
     অশান্ত
    0.60
     deste
    0.56
    த்துக்கு
    0.52
     तोला
    0.52
    Shortly
    0.51
     สุด
    0.51
    Periodic
    0.51
     izv
    0.51
    herin
    0.51
    𝒍
    0.50
    POSITIVE LOGITS
     harms
    0.52
    ᡠ
    0.52
    വെ
    0.51
    ண்கள்
    0.51
     ve
    0.49
     persec
    0.49
     marbles
    0.48
     appalled
    0.48
     zá
    0.47
    ன்மை
    0.47
    Activations Density 0.273%

    No Known Activations