© 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. 6375
    Prev
    Next
    INDEX
    Explanations

    Midjourney

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

    The neuron activates on mentions of bathroom amenities (e.g. hairdryers, toiletries).

    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
    но
    0.77
    ет
    0.74
    ку
    0.74
    на
    0.73
    ре
    0.73
    ту
    0.72
    т
    0.72
     grounds
    0.71
     divulg
    0.71
    আ
    0.70
    POSITIVE LOGITS
     سره
    0.86
     intentos
    0.85
     Juz
    0.85
     Daryl
    0.83
     Hadid
    0.83
     Coney
    0.83
     Более
    0.82
     Maloney
    0.82
     Boyle
    0.81
     Makin
    0.81
    Activations Density 0.001%

    No Known Activations