© 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. 10827
    Prev
    Next
    INDEX
    Explanations

    This neuron is a positional counter that fires most strongly on tokens near the start of the text (with activation decaying as the sequence progresses).

    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
    않
    0.89
    ↵↵
    0.80
    ap
    0.77
    ных
    0.75
          
    0.71
     }(
    0.71
    p
    0.70
    aney
    0.69
    am
    0.68
     Op
    0.68
    POSITIVE LOGITS
     plötzlich
    0.88
     ঝাঁপ
    0.86
     Ừ
    0.83
     doubting
    0.82
    ెం
    0.81
    ከት
    0.81
    ्वती
    0.80
     carburetor
    0.80
    до
    0.76
    绍
    0.75
    Activations Density 0.001%

    No Known Activations