© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12365
    Prev
    Next
    INDEX
    Explanations

    past, lifetime, precondition, pressing, lush

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

    creative juices flowing

    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
    :
    0.76
    immagine
    0.47
    ः
    0.46
     आणि
    0.45
    дной
    0.45
    िलेश
    0.44
    :“
    0.44
    ؟
    0.43
    бычно
    0.42
     होईल
    0.42
    POSITIVE LOGITS
     অন্যান্য
    0.46
     to
    0.45
     be
    0.44
    in
    0.41
    1
    0.41
    o
    0.39
    
    0.38
    b
    0.37
     resetCounters
    0.35
    ôtels
    0.35
    Activations Density 1.090%

    No Known Activations