© 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. 169
    Prev
    Next
    INDEX
    Explanations

    This neuron primarily detects the start‐of‐sentence marker and the key noun or topic words that follow it.

    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
     на
    0.26
     of
    0.24
     по
    0.24
     striped
    0.24
     reddish
    0.24
     spurious
    0.24
    2
    0.23
     yellowish
    0.23
    ただし
    0.23
    ಪ
    0.23
    POSITIVE LOGITS
    !?
    0.39
    !!
    0.39
     BECAUSE
    0.38
     aswell
    0.37
    !
    0.37
     nonostante
    0.36
     obwohl
    0.36
    เพราะ
    0.36
     porque
    0.35
    !।
    0.34
    Activations Density 15.772%

    No Known Activations