© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 996
    Prev
    Next
    INDEX
    Explanations

    special characters and encoding artifacts

    np_acts-logits-general · gemini-2.5-flash-lite

    chemical formulas and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    Sulf
    0.21
    ‒
    0.21
     narcotics
    0.21
     seawater
    0.21
    箖
    0.21
     geochemical
    0.21
    গানি
    0.21
    ...",
    0.20
     biofilms
    0.20
    ..'
    0.20
    POSITIVE LOGITS
    <0x9E>
    0.31
    <0x8C>
    0.27
    <0x95>
    0.27
    <0x81>
    0.25
    <0xA4>
    0.25
    <0x8A>
    0.25
    <0xA3>
    0.25
    <0xAD>
    0.25
    <0xB0>
    0.25
    <0x88>
    0.25
    Activations Density 0.024%

    No Known Activations