© 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. 12147
    Prev
    Next
    INDEX
    Explanations

    sentenced to probation or suspended sentence

    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
     sentimientos
    -0.80
    zw
    -0.76
    ==-
    -0.74
     bilder
    -0.73
     GHz
    -0.73
     SOUL
    -0.73
    MPH
    -0.71
    茹で
    -0.71
     اسک
    -0.71
     vícti
    -0.70
    POSITIVE LOGITS
     probation
    1.64
     deferred
    1.24
     suspended
    1.11
    prob
    1.08
     prob
    0.95
     conditional
    0.93
     avoid
    0.93
    conditional
    0.90
    suspended
    0.87
     community
    0.86
    Activations Density 0.029%

    No Known Activations