© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9094
    Prev
    Next
    INDEX
    Explanations

    The neuron flags the single most topically distinctive content word in each passage (the TF–IDF “peak”).

    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
    ی
    0.89
    וס
    0.85
    و
    0.82
     instilled
    0.80
    ה
    0.79
    Heating
    0.75
    Đ
    0.74
    མ
    0.74
     sufficient
    0.73
    সাম
    0.73
    POSITIVE LOGITS
     апреле
    0.89
     неделю
    0.85
     యూని
    0.79
     slä
    0.78
    бавить
    0.77
    吒
    0.77
     perda
    0.75
    éraire
    0.75
     Frente
    0.73
     себя
    0.73
    Activations Density 0.000%

    No Known Activations