© 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. 14265
    Prev
    Next
    INDEX
    Explanations

    pregnancy and progression

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

    The neuron strongly activates on the final content word just before a sentence-ending boundary.

    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
    IZED
    0.86
    ньо
    0.79
    Wasser
    0.79
    𝙚
    0.76
    ૂર્ણ
    0.74
    द्दाख
    0.74
    クマ
    0.73
    પ્ત
    0.73
     Mub
    0.72
    ાઈ
    0.71
    POSITIVE LOGITS
     Dolores
    0.90
     mutter
    0.89
     देखते
    0.78
     अधिवक्ता
    0.78
    O
    0.77
    டன்
    0.76
     vich
    0.75
    ción
    0.74
     denen
    0.73
    Dol
    0.73
    Activations Density 0.000%

    No Known Activations