© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5535
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on segments that present personal name meanings and origins (e.g. baby-name definition entries).

    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
    !);
    0.40
    !<
    0.37
    bevel
    0.36
    揀
    0.36
     نرخ
    0.36
     алыңыз
    0.36
    !;
    0.36
     preços
    0.35
     plod
    0.35
    cycled
    0.35
    POSITIVE LOGITS
     Sebagai
    0.44
     Daarnaast
    0.44
     Beside
    0.43
     Khy
    0.42
     Adik
    0.41
     Peshawar
    0.40
     Sexual
    0.40
    뿐
    0.39
     Gymn
    0.38
     Polaribacter
    0.38
    Activations Density 0.026%

    No Known Activations