© 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. 116672
    Prev
    Next
    INDEX
    Explanations

    service interaction and polite behavior

    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
     betroffen
    -0.84
     milioni
    -0.82
    rn
    -0.81
     from
    -0.79
    preuves
    -0.78
    arschijnlijk
    -0.77
    FFER
    -0.77
    gulan
    -0.76
     graders
    -0.76
     melanjutkan
    -0.75
    POSITIVE LOGITS
     behave
    1.39
     behaviour
    1.35
     behavior
    1.34
     attitude
    1.31
     approach
    1.27
     assist
    1.24
     guide
    1.24
     explaining
    1.20
     behaved
    1.16
     behaving
    1.15
    Activations Density 0.011%

    No Known Activations