© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1404
    Prev
    Next
    INDEX
    Explanations

    asking "what"

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

    This neuron responds to mentions of a delicatessen (specifically the word “Delicatessen”).

    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
     quanh
    0.78
     Threatened
    0.73
     Agreements
    0.72
    }$(
    0.72
     Fighters
    0.72
    ,
    0.69
     Minor
    0.67
     Scheme
    0.67
     Sees
    0.66
     -------------
    0.66
    POSITIVE LOGITS
    ш
    0.89
    ي
    0.86
    𝚓
    0.85
    ATG
    0.84
    ज
    0.83
    翻訳
    0.82
    詠
    0.81
    ᱩ
    0.80
    نا
    0.79
    ộng
    0.79
    Activations Density 0.000%

    No Known Activations