© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10189
    Prev
    Next
    INDEX
    Explanations

    organization and breakdown

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

    The neuron detects numeric values expressed with decimal points (i.e. floating-point numbers).

    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
    N
    0.84
    п
    0.82
    γγελ
    0.76
    NAM
    0.75
    必要な
    0.73
    GEBURTS
    0.73
    NAN
    0.73
     اگه
    0.72
     डिस्क्रिप्शन
    0.71
    ﻧ
    0.71
    POSITIVE LOGITS
    𝓲
    0.85
     THINK
    0.81
    lerimiz
    0.80
    ią
    0.79
     الشيخ
    0.79
    ילה
    0.77
    yati
    0.77
     dimers
    0.74
    तिरिक्त
    0.73
    𝓪
    0.72
    Activations Density 0.000%

    No Known Activations