© 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. 9950
    Prev
    Next
    INDEX
    Explanations

    movie titles

    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
     രോഗ
    0.90
    евского
    0.85
    েম
    0.83
    澱
    0.80
     prospective
    0.77
    రి
    0.77
    전에
    0.76
    太郎
    0.75
    ೆ
    0.75
    小学校
    0.74
    POSITIVE LOGITS
    leiding
    0.85
     dyr
    0.84
    liqu
    0.80
    ardan
    0.79
     mods
    0.79
    erset
    0.76
    actin
    0.75
    mour
    0.74
     présenter
    0.73
    lag
    0.72
    Activations Density 0.040%

    No Known Activations