© 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. 3865
    Prev
    Next
    INDEX
    Explanations

    code, UI, template, travel, model components

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

    The main thing this neuron does is detect web‐related service and development terms (e.g. “WEB,” “APP,” “WEBSITE,” “TEMPLATE”).

    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
     The
    0.63
    The
    0.63
    Sistema
    0.62
    Gruppe
    0.62
     Lank
    0.61
    Remarks
    0.61
    群
    0.61
    。
    0.60
    事業
    0.58
    Mga
    0.58
    POSITIVE LOGITS
    以外の
    0.71
     liés
    0.61
     embossing
    0.61
     transluc
    0.59
     spécifique
    0.56
     decals
    0.56
     schneller
    0.56
     músicos
    0.56
     facendo
    0.55
     reductase
    0.54
    Activations Density 0.044%

    No Known Activations