© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16294
    Prev
    Next
    INDEX
    Explanations

    times ending in pm

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

    code structure and syntax

    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
     леп
    0.43
     அபி
    0.42
    상은
    0.41
    ſs
    0.40
     совершенно
    0.40
    鸮
    0.40
     ఇది
    0.39
    缛
    0.39
     ऑस्ट्रेलियाई
    0.39
    ж
    0.39
    POSITIVE LOGITS
     intersects
    0.43
     intersect
    0.39
     intersected
    0.38
     shut
    0.38
     Wenn
    0.37
     lampu
    0.36
     cannot
    0.36
     loop
    0.36
     roared
    0.35
     gasped
    0.35
    Activations Density 0.011%

    No Known Activations