© 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. 16209
    Prev
    Next
    INDEX
    Explanations

    start of list or sequence

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

    The neuron responds most strongly to rare or low‐frequency tokens in the text.

    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
     экскур
    0.90
     پول
    0.86
    🍃
    0.84
    درسة
    0.84
     chloroplast
    0.83
     Mert
    0.81
     Søren
    0.79
     Vereinig
    0.79
    Editar
    0.79
     hippocampal
    0.78
    POSITIVE LOGITS
    ur
    0.85
    ase
    0.83
    ores
    0.80
    备
    0.78
    遗憾
    0.77
    um
    0.76
    il
    0.75
    kas
    0.74
    ilung
    0.72
    ans
    0.70
    Activations Density 0.000%

    No Known Activations