© 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. 115697
    Prev
    Next
    INDEX
    Explanations

    greetings, messages, and farewells

    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
     approve
    -0.83
    żesz
    -0.81
     approved
    -0.81
     adjuvant
    -0.77
    ETHOD
    -0.76
    WEATHER
    -0.75
    déric
    -0.74
    olisian
    -0.73
    enerbah
    -0.73
     inquis
    -0.72
    POSITIVE LOGITS
     letter
    1.22
     message
    1.20
    atory
    1.17
     messages
    1.15
     letters
    1.13
    状
    1.08
    ductory
    1.07
     note
    1.03
    Letter
    1.02
     ceremony
    0.98
    Activations Density 0.032%

    No Known Activations