© 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. 34-GEMMASCOPE-RES-131K
    7. 84812
    Prev
    Next
    INDEX
    Explanations

    joining code blocks

    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
    返し
    -0.85
     partnerships
    -0.73
    rifugal
    -0.73
    不夠
    -0.73
    änner
    -0.73
    Fixtures
    -0.72
    ={};
    -0.72
    ūsu
    -0.72
     Partnerships
    -0.71
    ีย์
    -0.71
    POSITIVE LOGITS
     join
    3.53
    join
    3.45
     joined
    3.08
     joining
    2.97
     Join
    2.91
    Join
    2.84
     joins
    2.83
    JOIN
    2.75
     JOIN
    2.59
    joined
    2.45
    Activations Density 0.013%

    No Known Activations