© 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. 33551
    Prev
    Next
    INDEX
    Explanations

    when or imagine

    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
     and
    -1.78
     lakini
    -1.45
     but
    -1.39
     however
    -1.20
     però
    -1.17
    .‏
    -1.15
    therefore
    -1.13
    wa
    -1.13
    ys
    -1.07
    싶
    -1.06
    POSITIVE LOGITS
     when
    1.88
    When
    1.87
    Imagine
    1.77
     когда
    1.75
     imagine
    1.72
     it
    1.66
     It
    1.63
     Imagine
    1.61
    It
    1.60
     Lorsque
    1.51
    Activations Density 0.299%

    No Known Activations