© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115605
    Prev
    Next
    INDEX
    Explanations

    evidence of or for

    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_34/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
    ين
    -0.98
    刻
    -0.97
    fixture
    -0.94
     гораздо
    -0.93
     perfectly
    -0.92
    daki
    -0.90
     кра
    -0.88
    Notable
    -0.86
     conjunction
    -0.84
    寓
    -0.84
    POSITIVE LOGITS
     of
    1.50
     suggests
    1.31
     adduced
    1.26
     presented
    1.24
    presented
    1.09
     that
    1.05
     presentó
    1.05
    柠
    1.04
    rement
    1.01
    custo
    1.00
    Activations Density 0.027%

    No Known Activations