© 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. 1967
    Prev
    Next
    INDEX
    Explanations

    continuation after "you"

    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
     스마트
    1.39
     mentors
    1.39
     젊
    1.36
    jenja
    1.32
    apatkan
    1.31
     포인트
    1.31
     뽑
    1.29
     프로그램을
    1.28
     terbaik
    1.27
     커
    1.26
    POSITIVE LOGITS
     prohibition
    1.60
     violations
    1.54
     violation
    1.53
     prohibiting
    1.52
     prohib
    1.50
     violating
    1.46
     prohibitions
    1.45
     exempted
    1.45
     нарушение
    1.40
     exempt
    1.38
    Activations Density 0.644%

    No Known Activations