© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7181
    Prev
    Next
    INDEX
    Explanations

    foreign languages and Arabic words

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

    The neuron fires on tokens that signal “there’s more to read” (ellipsis markers like “…” and continuation cues such as “more” or “Continue”).

    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
    ldon
    0.80
    lds
    0.68
    vés
    0.67
    لڈ
    0.66
    퓰
    0.65
    LH
    0.64
    fj
    0.63
    ld
    0.63
    SCO
    0.63
    }?
    0.63
    POSITIVE LOGITS
     matte
    0.70
     tappa
    0.68
     miejscu
    0.66
     lokale
    0.65
     walnuts
    0.65
     وہاں
    0.64
     deewana
    0.64
     गणपति
    0.63
     mailing
    0.63
     barang
    0.63
    Activations Density 0.004%

    No Known Activations