© 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. 11569
    Prev
    Next
    INDEX
    Explanations

    not usually worry too much

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

    The neuron fires on hedging or softening expressions—those “maybe,” “not too,” “you’re not concerned”–style phrases that qualify or downplay statements.

    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
     yet
    0.63
     properly
    0.59
     võimalik
    0.58
    yet
    0.57
    ]==
    0.56
    appropriate
    0.56
     volle
    0.56
    understand
    0.55
    𝐞
    0.55
    !!
    0.55
    POSITIVE LOGITS
    เสียหาย
    0.80
     Couldn
    0.78
     크게
    0.75
     অসুবিধা
    0.71
     great
    0.67
     Surprisingly
    0.66
    great
    0.65
     objection
    0.64
     nagy
    0.64
     ক্ষতির
    0.64
    Activations Density 0.276%

    No Known Activations