© 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. 2045
    Prev
    Next
    INDEX
    Explanations

    but

    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
    可惜
    -1.10
     zwar
    -1.05
    unfortunately
    -1.02
    のですが
    -0.97
     unfortunately
    -0.92
    çoise
    -0.91
    '&
    -0.90
     allerdings
    -0.88
     THOUGH
    -0.88
    ❌
    -0.87
    POSITIVE LOGITS
     hey
    4.09
    Hey
    3.06
    hey
    2.83
     Hey
    2.75
     who
    2.08
    HEY
    1.95
     HEY
    1.84
    Who
    1.73
     then
    1.72
     beggars
    1.56
    Activations Density 0.044%

    No Known Activations