© 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. 4484
    Prev
    Next
    INDEX
    Explanations

    storytelling and history in various languages

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

    This neuron detects references to history or archaeology (e.g. occurrences of "history," "archaeology," or similar historical domain 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
    м
    1.09
    ра
    1.09
    })$,
    1.04
    س
    1.04
    CIES
    1.03
     severed
    1.03
    <0x80>
    0.99
    MENTS
    0.98
    ментом
    0.96
    с
    0.96
    POSITIVE LOGITS
    history
    1.74
     história
    1.67
     sejarah
    1.58
    历史
    1.55
    jarah
    1.52
    histo
    1.52
     историю
    1.52
     historia
    1.51
     ইতিহাস
    1.49
     storia
    1.46
    Activations Density 0.171%

    No Known Activations