© 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. 15513
    Prev
    Next
    INDEX
    Explanations

    linking to other things

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

    The neuron is primarily responding to numeric tokens and measurements (digits, decimal numbers, distances, statistics, etc.).

    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
    ć
    0.80
    ey
    0.80
     Anzahl
    0.80
    CREATED
    0.78
    LINE
    0.74
    рё
    0.74
    ки
    0.73
    titled
    0.73
    aj
    0.73
    tete
    0.73
    POSITIVE LOGITS
    やっと
    0.80
     cartons
    0.79
    ເຮັດ
    0.78
     conseg
    0.76
     compres
    0.75
     ◆
    0.74
     fumes
    0.73
     పూర్తిగా
    0.73
     ทำให้
    0.72
     scraps
    0.72
    Activations Density 0.000%

    No Known Activations