© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 16127
    Prev
    Next
    INDEX
    Explanations

    hallucinations and fabrications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     grin
    0.86
     patronage
    0.79
    ceptible
    0.77
    iah
    0.77
    AKI
    0.76
     JSTOR
    0.75
    าม
    0.74
    ฮ
    0.72
     strike
    0.72
     pediatric
    0.72
    POSITIVE LOGITS
     Ü
    1.01
    锦
    0.99
     Fl
    0.96
     কম্প
    0.94
    流
    0.93
    最后一个
    0.92
     lac
    0.92
     Ú
    0.91
    olí
    0.90
    냉
    0.89
    Activations Density 0.180%

    No Known Activations