© 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. 38632
    Prev
    Next
    INDEX
    Explanations

    law offenders and wrongdoing

    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
     assassinated
    -1.00
     mutilated
    -0.92
     jealousy
    -0.84
     persecuted
    -0.81
     strangled
    -0.80
     strangest
    -0.79
     unspeak
    -0.77
     シングル
    -0.77
     testator
    -0.76
     étrang
    -0.76
    POSITIVE LOGITS
     offenders
    2.67
     offending
    2.59
     guilty
    2.36
     offender
    2.31
     err
    2.30
     delinquent
    2.09
     vio
    2.03
     transgress
    1.99
     culprit
    1.98
     defa
    1.89
    Activations Density 0.105%

    No Known Activations