© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13668
    Prev
    Next
    INDEX
    Explanations

    original Apple product

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

    The neuron flags unusually rare or uncommon 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
     Lebensmittel
    0.89
     SCGS
    0.84
     Señ
    0.79
     COSTS
    0.75
     ASME
    0.74
    ത്തിലേക്ക്
    0.74
     Вікіпедії
    0.74
    煊
    0.73
     Standards
    0.73
     QUESTIONS
    0.73
    POSITIVE LOGITS
    dt
    0.83
    hia
    0.81
    t
    0.79
    좇
    0.76
     draper
    0.75
    пы
    0.73
    ič
    0.73
     allevi
    0.73
     graced
    0.73
    ri
    0.73
    Activations Density 0.000%

    No Known Activations