© 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. 14129
    Prev
    Next
    INDEX
    Explanations

    angle, width, annual, properties

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

    This neuron lights up on the very first “real” token at the start of each text segment (i.e. the first non‐padding word after the <start> marker).

    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
     esattamente
    0.86
    🗾
    0.85
     entusias
    0.83
     关于
    0.83
     worldRank
    0.81
    🗻
    0.80
    แก้ไข
    0.80
    🌏
    0.79
    🏞
    0.79
    講解
    0.78
    POSITIVE LOGITS
    -
    0.87
     hearth
    0.84
    ه
    0.82
     Rumble
    0.74
    JlcG
    0.71
    op
    0.71
    COME
    0.71
    ون
    0.70
    ت
    0.70
    ot
    0.68
    Activations Density 0.001%

    No Known Activations