© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2436
    Prev
    Next
    INDEX
    Explanations

    Title and headings

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

    The neuron activates on tokens that specify centering or center alignment in document formatting instructions.

    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
     tasked
    0.77
     вле
    0.66
     främ
    0.65
    蠻
    0.64
    ᧐
    0.64
    佔
    0.64
     dueño
    0.63
    /
    0.63
    隣
    0.62
     dź
    0.62
    POSITIVE LOGITS
    filenames
    0.80
    TITLE
    0.80
    LLCATS
    0.79
    levelname
    0.79
    IZONTAL
    0.78
    ΡΑ
    0.77
    ijkl
    0.77
    ონის
    0.77
    dropout
    0.75
    وها
    0.74
    Activations Density 0.000%

    No Known Activations