© 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. 12120
    Prev
    Next
    INDEX
    Explanations

    music, borrower, game, lenses

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

    The neuron responds to salient, content-bearing nouns—especially named entities and domain-specific topic terms.

    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
     সুই
    0.66
     plaintext
    0.59
    してみました
    0.59
    এফ
    0.59
     класу
    0.59
    所谓的
    0.58
    出一个
    0.56
     यी
    0.56
     класса
    0.55
    的這個
    0.55
    POSITIVE LOGITS
    ovní
    0.65
     also
    0.64
     też
    0.64
     Debit
    0.64
    及
    0.64
     myös
    0.61
    Input
    0.60
     aussi
    0.59
    Consult
    0.59
     zároveň
    0.59
    Activations Density 0.310%

    No Known Activations