© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30977
    Prev
    Next
    INDEX
    Explanations

    join operations

    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
     concep
    -0.85
     vald
    -0.84
     gasolina
    -0.83
     ſou
    -0.82
    佤
    -0.82
     bapt
    -0.81
    secuencias
    -0.81
     goose
    -0.79
    risas
    -0.76
     OCH
    -0.76
    POSITIVE LOGITS
     join
    1.25
    Join
    1.09
     Join
    1.03
     joined
    1.02
    join
    1.02
     joining
    0.93
     Joining
    0.91
     joins
    0.86
     count
    0.86
     rejoin
    0.83
    Activations Density 0.042%

    No Known Activations