© 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. 77181
    Prev
    Next
    INDEX
    Explanations

    reduce unwanted effects

    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
     grise
    -0.89
     uninten
    -0.87
     alha
    -0.84
     vandal
    -0.83
    鎊
    -0.82
     gradation
    -0.81
     sable
    -0.79
     rupt
    -0.79
     alun
    -0.79
     treads
    -0.79
    POSITIVE LOGITS
    undes
    1.02
     excessive
    0.94
     tendency
    0.92
     undesirable
    0.90
     unacceptable
    0.90
     undes
    0.89
     unwanted
    0.88
     tendencies
    0.88
     Zudem
    0.87
    ballo
    0.84
    Activations Density 0.031%

    No Known Activations