© 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. 1745
    Prev
    Next
    INDEX
    Explanations

    subjected to negative experiences

    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
     PROBLE
    -0.98
    Obituary
    -0.91
    Recovered
    -0.88
    するの
    -0.84
    Proble
    -0.82
     berangkat
    -0.82
    
    -0.81
     tragic
    -0.81
     écou
    -0.80
     ruins
    -0.80
    POSITIVE LOGITS
     treated
    1.77
     ignored
    1.70
     exploited
    1.48
     lied
    1.47
     abused
    1.45
     subjected
    1.36
    treated
    1.34
     discriminated
    1.34
     cheated
    1.30
    被
    1.29
    Activations Density 0.041%

    No Known Activations