© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93296
    Prev
    Next
    INDEX
    Explanations

    childhood trauma and past suffering

    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
     herre
    -1.01
     inger
    -1.01
     sels
    -0.94
     filmp
    -0.90
    üll
    -0.89
     bren
    -0.89
     olie
    -0.88
     lage
    -0.87
     nage
    -0.86
    gn
    -0.85
    POSITIVE LOGITS
     childhood
    2.58
     trauma
    2.39
     traumatic
    2.33
     past
    2.20
     experiences
    2.02
     upbringing
    1.97
     history
    1.91
    trauma
    1.85
     traum
    1.76
     backstory
    1.74
    Activations Density 0.052%

    No Known Activations