© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9156
    Prev
    Next
    INDEX
    Explanations

    attribute selectors like `[id*=""]`

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

    The neuron fires on hyperlink markup and URL tokens, i.e. anything resembling an embedded link or URL attribute.

    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
    {\
    0.68
    head
    0.67
    }}}
    0.64
    ({\
    0.60
    ]
    0.60
     comm
    0.59
    บู
    0.59
    ի
    0.57
    ५
    0.57
    ube
    0.55
    POSITIVE LOGITS
     príncipe
    0.61
     duit
    0.59
     деву
    0.59
     Pompeo
    0.59
     îl
    0.59
     espectacular
    0.59
     indivíduos
    0.58
     Тран
    0.58
     delitos
    0.58
     Aragón
    0.58
    Activations Density 0.000%

    No Known Activations