© 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. 77002
    Prev
    Next
    INDEX
    Explanations

    doing it right or wrong

    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
     undergoing
    -1.05
     doing
    -1.01
     being
    -0.96
     behaving
    -0.95
     happenings
    -0.90
     performing
    -0.88
     realização
    -0.88
     conducted
    -0.86
     saying
    -0.85
     happening
    -0.85
    POSITIVE LOGITS
     wrong
    1.52
     differently
    1.16
     with
    1.13
     right
    0.99
     RIGHT
    0.91
     WRONG
    0.90
    wrong
    0.89
     justice
    0.86
     without
    0.83
     správ
    0.83
    Activations Density 0.047%

    No Known Activations