© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36203
    Prev
    Next
    INDEX
    Explanations

    programming data types and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TB
    -0.99
    A
    -0.96
    Beach
    -0.89
    说过
    -0.89
     安心
    -0.88
    了一句
    -0.86
    と
    -0.85
    像
    -0.85
    や
    -0.85
     一人
    -0.85
    POSITIVE LOGITS
    rassed
    1.02
    绛
    1.00
     of
    0.97
    riente
    0.91
    
    0.91
    ěli
    0.90
    \",\
    0.89
    logne
    0.88
    entia
    0.86
    Ɏ
    0.86
    Activations Density 0.017%

    No Known Activations