© 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-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1027
    Prev
    Next
    INDEX
    Explanations

    mental health

    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_17_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
    Congratulations
    0.80
    Congrats
    0.78
    ที่
    0.75
    http
    0.74
    “…
    0.73
    なんと
    0.72
    昨
    0.70
    떴
    0.70
    …”
    0.68
    ที่จะ
    0.67
    POSITIVE LOGITS
     OTHER
    1.27
     Otros
    1.25
    autres
    1.23
     otros
    1.22
     Miscellaneous
    1.20
     kategori
    1.17
     Other
    1.16
     Kategor
    1.15
     ஏற்பட
    1.14
     Otras
    1.14
    Activations Density 0.600%

    No Known Activations