© 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. 11080
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions

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

    The neuron flags content‐heavy, domain‐specific terminology—i.e. specialized jargon and technical nouns.

    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
     TikTok
    0.89
     మరియు
    0.88
     ✅
    0.86
     tiktok
    0.85
     এবং
    0.85
     LGBTQ
    0.84
     🥰
    0.83
    ＆
    0.82
    Emojis
    0.80
    🤍
    0.80
    POSITIVE LOGITS
    avirus
    0.76
    计算机
    0.74
     expenditures
    0.74
     catastrophes
    0.74
     reorganization
    0.70
    故障
    0.69
    病例
    0.69
    ruptcy
    0.68
    ricanes
    0.68
    ometime
    0.68
    Activations Density 0.079%

    No Known Activations