© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    feeling emotional states

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

    The neuron activates on numeric tokens (including numbers with decimal points).

    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
    é
    1.55
    ри
    1.46
    k
    1.45
    ين
    1.44
    ни
    1.36
    ك
    1.32
    ために
    1.28
    nake
    1.28
    ру
    1.25
    IFICATION
    1.24
    POSITIVE LOGITS
    ि
    1.27
     وحتى
    1.23
    同様
    1.22
    ÇÕES
    1.21
     éprou
    1.20
    陇
    1.20
    Doors
    1.15
    ऽ
    1.15
    Hora
    1.13
    ॉकलेट
    1.11
    Activations Density 0.078%

    No Known Activations