© 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. 1706
    Prev
    Next
    INDEX
    Explanations

    foreign language content

    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
     safeguard
    1.59
     khoản
    1.52
     assessment
    1.45
     unenforceable
    1.44
     recruitment
    1.44
    ‍♂️
    1.42
    ({});
    1.40
    搬型
    1.40
    ‍♀️
    1.39
     dưỡng
    1.38
    POSITIVE LOGITS
    有點
    1.57
    ripe
    1.57
     لديك
    1.52
    rovers
    1.51
     عندي
    1.49
     awhile
    1.49
    س
    1.48
     جدا
    1.47
    really
    1.47
    მი
    1.47
    Activations Density 0.000%

    No Known Activations