© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6415
    Prev
    Next
    INDEX
    Explanations

    Visual Pleasure and Vicuna models

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

    The neuron is strongly activated by tokens that come from web‐style listings and URLs—e.g. domain names, query‐string parameters, and product/manufacturer listing phrases.

    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_31_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
     রাতের
    0.70
    鬚
    0.57
    itamos
    0.56
    සිය
    0.56
    jecha
    0.55
     mistura
    0.54
    PEZ
    0.53
     każdej
    0.52
    MouseEnter
    0.52
     ------------
    0.52
    POSITIVE LOGITS
     Vn
    0.57
    ொழுது
    0.55
    †
    0.50
     zelo
    0.49
     Vr
    0.48
    пки
    0.48
    するための
    0.48
     MenuView
    0.48
     रवि
    0.47
     Pv
    0.47
    Activations Density 0.277%

    No Known Activations