© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9564
    Prev
    Next
    INDEX
    Explanations

    Federal Trade Commission acronym

    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_22_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
    抖
    0.90
    تح
    0.88
    <unused1870>
    0.84
    Tester
    0.84
    rsvp
    0.83
     رجسٹر
    0.83
    <unused1150>
    0.82
    .%
    0.82
    壹百
    0.82
    anonymous
    0.81
    POSITIVE LOGITS
     tradition
    0.99
    ahiya
    0.91
    であることが
    0.90
     traditions
    0.88
     normalement
    0.88
    𝙶
    0.87
     cytokinin
    0.86
     monarchy
    0.85
    ന്നെ
    0.85
     Shade
    0.84
    Activations Density 0.019%

    No Known Activations