© 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. 15896
    Prev
    Next
    INDEX
    Explanations

    code parameters and types

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

    This neuron responds to unusually long word tokens (i.e. multi-syllable, high-character-count 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
     Это
    0.78
     основные
    0.77
     মেডি
    0.76
    ены
    0.75
    нес
    0.74
    шина
    0.73
     энер
    0.71
    </h2>
    0.71
     newest
    0.70
     آرام
    0.70
    POSITIVE LOGITS
    יה
    0.84
     Pandya
    0.84
    ಪಿ
    0.83
    ಮೊ
    0.83
     respectivement
    0.83
     combien
    0.81
    ಎಂ
    0.80
     raffin
    0.80
     miliardi
    0.79
    یا
    0.79
    Activations Density 0.000%

    No Known Activations