© 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. 4800
    Prev
    Next
    INDEX
    Explanations

    DCF, cold, trained, arg, Alternative, bad, standalone, const

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

    The neuron selectively activates on the journal‐name strings and adjoining volume/issue numbers of bibliographic citations.

    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
     жить
    0.79
    ItemId
    0.78
    FALSE
    0.78
    త్వ
    0.77
     알
    0.76
     wap
    0.75
    ING
    0.74
    LoginID
    0.72
    managing
    0.72
    NE
    0.72
    POSITIVE LOGITS
    蕈
    0.80
    atud
    0.72
     kişilik
    0.72
    ⁍
    0.71
     Populations
    0.71
     Distributions
    0.70
    俩
    0.70
    ことを
    0.70
     suất
    0.69
    érm
    0.69
    Activations Density 0.001%

    No Known Activations