© 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. 38638
    Prev
    Next
    INDEX
    Explanations

    greeting or invitation

    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
     dano
    -0.79
     appuntamento
    -0.77
    verb
    -0.76
    kDa
    -0.75
     تغ
    -0.71
     kedai
    -0.70
     Numéro
    -0.70
    ument
    -0.69
    inske
    -0.69
    зме
    -0.68
    POSITIVE LOGITS
     say
    4.06
    Say
    3.53
    say
    3.38
     Say
    3.34
     SAY
    2.72
    SAY
    2.47
     hello
    2.42
     saying
    2.23
     says
    2.00
     introduce
    1.86
    Activations Density 0.032%

    No Known Activations