© 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. 13944
    Prev
    Next
    INDEX
    Explanations

    worth remembering

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

    The neuron strongly fires on the very first word of each text chunk or sentence‐segment (i.e. tokens immediately following a <start> or new‐paragraph boundary).

    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
     ≥
    0.69
     PGR
    0.69
     अपना
    0.68
     발생하는
    0.68
     GWAS
    0.67
    iert
    0.65
     धारण
    0.65
    aints
    0.64
    achten
    0.64
    wehr
    0.64
    POSITIVE LOGITS
    蘋果
    0.79
    ٠
    0.77
    在這
    0.76
    મો
    0.74
    Retail
    0.73
    かもしれない
    0.73
     correctes
    0.73
    誐
    0.73
    ૦
    0.73
    鎚
    0.71
    Activations Density 0.942%

    No Known Activations