© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10344
    Prev
    Next
    INDEX
    Explanations

    telegram bot

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

    The neuron is specialized to detect mentions of the Telegram messaging service (and related chat‐app references).

    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_31_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
     소프트
    0.61
    ソフトウェア
    0.54
    昧
    0.53
    workItem
    0.52
    蛀
    0.52
     DEJ
    0.52
    衄
    0.51
    🚭
    0.50
    ヨーク
    0.49
    iodo
    0.49
    POSITIVE LOGITS
     Telegram
    1.59
    Telegram
    1.56
     telegram
    1.50
     bot
    1.44
     Bot
    1.40
    Bot
    1.34
    bot
    1.31
    telegram
    1.31
     BOT
    1.26
     bots
    1.17
    Activations Density 0.014%

    No Known Activations