© 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. 2116
    Prev
    Next
    INDEX
    Explanations

    return statements

    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
     aggregating
    0.72
    -
    0.71
     concentrating
    0.68
    -<
    0.68
     constituting
    0.66
     VII
    0.65
     containing
    0.65
    -/
    0.62
    \'
    0.61
     beating
    0.60
    POSITIVE LOGITS
     allora
    1.17
     Quindi
    1.09
     entonces
    1.07
     Então
    1.06
     lalu
    1.06
     Тогда
    1.06
     その
    1.05
     wówczas
    1.04
     znaj
    1.04
     لہ
    1.04
    Activations Density 0.017%

    No Known Activations