© 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. 16280
    Prev
    Next
    INDEX
    Explanations

    acronyms followed by parentheses

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

    Natural Language Processing

    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
     (
    0.63
    7
    0.54
     ({\
    0.50
    6
    0.50
     ([
    0.50
     (<
    0.49
     (-
    0.48
    8
    0.48
     (#
    0.47
     (‘
    0.46
    POSITIVE LOGITS
    寘
    0.42
     entweder
    0.40
     Either
    0.39
    没想到
    0.39
    演出
    0.38
     dlatego
    0.38
     einiger
    0.38
    洴
    0.38
    െല്ലാം
    0.38
     certains
    0.38
    Activations Density 0.041%

    No Known Activations