© 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. 9103
    Prev
    Next
    INDEX
    Explanations

    The neuron detects blog‐style metadata labels and their values (e.g. tag/category headings, “Tagged,” “Sale,” and other post‐metadata tokens).

    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
     C
    0.85
     R
    0.83
    IP
    0.83
    II
    0.82
    III
    0.81
     I
    0.81
    ER
    0.81
     A
    0.79
     N
    0.79
    v
    0.79
    POSITIVE LOGITS
     jotka
    0.96
    },
    0.93
     které
    0.93
     אשר
    0.89
     która
    0.89
     tačiau
    0.89
     takže
    0.89
     которая
    0.88
     shayari
    0.87
     tampering
    0.86
    Activations Density 0.331%

    No Known Activations