© 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. 13515
    Prev
    Next
    INDEX
    Explanations

    list index or parameter name

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

    The neuron flags tokens that are parts of URLs or web domain names (e.g. “twitter.com,” “cards,” “http,” etc.).

    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
     @
    1.12
     #
    0.97
     (@
    0.96
     @_
    0.85
     [@
    0.85
     "@
    0.81
    (@
    0.80
    ,@
    0.77
    @
    0.76
    .@
    0.75
    POSITIVE LOGITS
     pebbles
    0.58
    istán
    0.55
     pebb
    0.54
     heath
    0.54
    irmeye
    0.54
     stones
    0.52
     diversification
    0.51
    羽
    0.51
     নবী
    0.51
    timeline
    0.50
    Activations Density 0.057%

    No Known Activations