© 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. 63358
    Prev
    Next
    INDEX
    Explanations

    welcoming new people or things

    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
    锯
    -0.89
     reclamo
    -0.88
    }$​
    -0.86
     constantly
    -0.85
    ayangkan
    -0.84
     Therefore
    -0.84
    ות
    -0.84
     polecam
    -0.84
     prestigio
    -0.84
     meliputi
    -0.83
    POSITIVE LOGITS
     into
    1.92
    welcome
    1.78
     warmly
    1.74
     welcome
    1.65
     welcomed
    1.53
     welcomes
    1.49
     velkommen
    1.46
    Welcome
    1.45
     bienvenida
    1.39
     aboard
    1.35
    Activations Density 0.012%

    No Known Activations