© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108044
    Prev
    Next
    INDEX
    Explanations

    statements and reactions

    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
     belki
    -1.01
     PLEASE
    -0.94
     probably
    -0.90
     mengel
    -0.90
     может
    -0.87
     datang
    -0.85
     possibly
    -0.83
    vais
    -0.82
     csak
    -0.81
     sábado
    -0.81
    POSITIVE LOGITS
     remains
    1.36
     remain
    1.20
     note
    1.20
     fully
    1.10
     continue
    1.09
     disappointment
    1.05
     await
    1.04
     continúa
    1.03
     repeat
    1.03
     respect
    1.01
    Activations Density 0.029%

    No Known Activations