© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13678
    Prev
    Next
    INDEX
    Explanations

    time duration

    np_acts-logits-general · gemini-2.5-flash-lite

    indoor or doorway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
     ANGELES
    0.54
     diem
    0.49
     HUNT
    0.47
    는
    0.47
     memer
    0.45
     nombreuses
    0.45
    まな
    0.44
     mnemonic
    0.44
     TODOS
    0.43
     makeover
    0.43
    POSITIVE LOGITS
     যদি
    0.42
     প্রস্তাব
    0.41
    защи
    0.41
    zys
    0.41
    iverso
    0.41
    Percentages
    0.41
    رب
    0.40
    slidesPer
    0.40
     ശ
    0.39
     ஒப்பந்த
    0.39
    Activations Density 0.014%

    No Known Activations