© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12446
    Prev
    Next
    INDEX
    Explanations

    toxic responses, exclude, medical, intentionally

    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_7_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
    tam
    3.05
     dips
    2.74
    
    2.74
    ’’
    2.67
    اں
    2.67
     ‘’
    2.65
    sia
    2.61
     nedir
    2.58
    …’
    2.57
    loads
    2.55
    POSITIVE LOGITS
     PopupWindow
    2.75
    િ
    2.74
    isi
    2.71
    ТА
    2.64
    ির
    2.60
    िज
    2.59
    ულ
    2.59
    aric
    2.56
    Ь
    2.52
    тит
    2.49
    Activations Density 0.001%

    No Known Activations