© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13700
    Prev
    Next
    INDEX
    Explanations

    each followed by a specific item

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

    This neuron strongly activates on the word “Each,” i.e. it detects occurrences of the token “Each.”

    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_31_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
    lerinde
    0.84
     imaginable
    0.77
    populations
    0.76
    𝚂
    0.74
     কিছুই
    0.73
    あらゆる
    0.73
    อะไร
    0.72
    similar
    0.72
    
    0.71
    lerinden
    0.71
    POSITIVE LOGITS
     of
    1.20
     respective
    1.11
     jednotliv
    0.96
     successive
    0.95
     individual
    0.94
     jeweil
    0.91
     respectivos
    0.90
     respectivas
    0.86
     প্রত্যেকের
    0.86
    々の
    0.85
    Activations Density 0.089%

    No Known Activations