© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2254
    Prev
    Next
    INDEX
    Explanations

    amino acids

    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_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
     u
    0.99
     tái
    0.90
    ผล
    0.89
     começa
    0.89
     Ha
    0.86
     constitución
    0.84
     I
    0.83
     :
    0.83
     là
    0.82
     is
    0.82
    POSITIVE LOGITS
    miktar
    1.39
    spl
    1.25
    sustainable
    1.22
    <unused313>
    1.20
    𝙙
    1.17
    two
    1.16
    temporary
    1.15
    <unused975>
    1.15
    utely
    1.15
    approximately
    1.14
    Activations Density 0.515%

    No Known Activations