© 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. 7190
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to self or AI

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    рна
    0.57
     při
    0.52
    बाट
    0.49
     dina
    0.49
    迠
    0.48
    cycle
    0.47
    洊
    0.47
     rempl
    0.46
     rendement
    0.45
     cycle
    0.45
    POSITIVE LOGITS
     🙂
    0.74
     unsurprisingly
    0.66
     آسیب
    0.63
     অবশ্যই
    0.62
     প্রমুখ
    0.62
    )
    0.62
     パンツ
    0.60
     :)
    0.59
    稹
    0.59
    (!
    0.58
    Activations Density 0.090%

    No Known Activations