© 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. 11078
    Prev
    Next
    INDEX
    Explanations

    ish

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

    The neuron strongly activates on the first content word at the start of a new sentence or paragraph.

    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
     ministère
    0.80
     glanced
    0.78
    리소스
    0.78
    জিৎ
    0.73
     bassist
    0.72
    পৃ
    0.72
     contrasting
    0.71
    밍
    0.71
     sculptor
    0.71
    ין
    0.70
    POSITIVE LOGITS
    ˂
    0.96
    ία
    0.90
    ik
    0.82
    arashtra
    0.79
    araj
    0.76
    jach
    0.75
    و
    0.75
    estado
    0.75
    <>
    0.74
    ្ល
    0.74
    Activations Density 0.000%

    No Known Activations