© 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. 698
    Prev
    Next
    INDEX
    Explanations

    The neuron flags specific proper‐name entities—especially brand, organization, award, or other named‐entity mentions.

    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
    ﺼ
    0.44
    ColumnKind
    0.41
     cláus
    0.41
     Einf
    0.40
     emphatic
    0.39
    ริ
    0.39
    َد
    0.39
     Abgerufen
    0.39
    stituting
    0.39
     แก้
    0.39
    POSITIVE LOGITS
    aya
    0.47
    人和
    0.46
    wood
    0.46
    x
    0.45
    ar
    0.45
    meti
    0.44
    1
    0.44
     temples
    0.43
     എം
    0.43
    ay
    0.42
    Activations Density 0.000%

    No Known Activations