© 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-16K
    7. 1997
    Prev
    Next
    INDEX
    Explanations

    various languages and separators

    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_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
     Artur
    1.38
     turn
    1.37
     Wins
    1.30
    шке
    1.25
     Исто
    1.25
     своём
    1.25
    tope
    1.25
    愎
    1.24
     thắng
    1.23
     Case
    1.23
    POSITIVE LOGITS
    fum
    1.61
    fri
    1.61
    bury
    1.54
    a
    1.45
    frost
    1.40
    punctuation
    1.39
    brides
    1.37
    ritual
    1.35
    ynchronous
    1.33
    aar
    1.33
    Activations Density 0.000%

    No Known Activations