© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13306
    Prev
    Next
    INDEX
    Explanations

    box, gloves, character, grid, checks

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

    The neuron is tuned to very high‐frequency/common English tokens (i.e. commonplace “filler” words).

    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
     '
    0.71
     np
    0.70
     namesake
    0.68
     player
    0.66
     NP
    0.65
     eponymous
    0.65
        
    0.64
                
    0.63
    ذه
    0.63
    क
    0.63
    POSITIVE LOGITS
     学習
    0.90
    頨
    0.87
     AcOEt
    0.85
     acero
    0.85
     activación
    0.84
     Calcd
    0.84
     sıvı
    0.83
     composés
    0.81
     stoked
    0.81
     interfaz
    0.81
    Activations Density 0.000%

    No Known Activations