© 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. 3307
    Prev
    Next
    INDEX
    Explanations

    technical troubleshooting and solutions

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

    The neuron consistently lights up on substantive “open‐class” words (nouns, verbs, adjectives, pronouns) rather than on function words.

    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
     również
    1.09
    😲
    1.02
    📷
    0.99
    arrivalTime
    0.97
    据悉
    0.96
     এছাড়াও
    0.95
     পুনরায়
    0.95
     eventful
    0.95
    犹如
    0.94
    numOf
    0.92
    POSITIVE LOGITS
     I
    1.14
     Qaeda
    1.07
     libertarian
    1.05
     colleagues
    1.02
     Rawls
    1.01
     F
    1.00
     ought
    0.99
     Nietzsche
    0.99
     argues
    0.98
     arXiv
    0.98
    Activations Density 0.408%

    No Known Activations