© 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. 9475
    Prev
    Next
    INDEX
    Explanations

    Apple MacBook

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

    The neuron activates on words used in property or accommodation listings to describe capacity and features (e.g. "families," "accommodates," "has").

    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
    لكتر
    0.86
     親
    0.84
    遐
    0.84
    تس
    0.83
     চাহিয়া
    0.81
    ەك
    0.80
    ين
    0.79
    मियल
    0.79
    ستي
    0.77
    ینڈ
    0.76
    POSITIVE LOGITS
     |
    0.80
    |
    0.80
    IANS
    0.76
    ள்
    0.76
    lian
    0.75
    vmin
    0.74
    ი
    0.74
    amiento
    0.73
     bolsillo
    0.72
    间的
    0.72
    Activations Density 0.000%

    No Known Activations