© 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. 99535
    Prev
    Next
    INDEX
    Explanations

    sexual abuse and violence

    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
    Victim
    -0.92
    antikan
    -0.85
     geography
    -0.85
     varones
    -0.85
     geology
    -0.82
     INVESTIGATION
    -0.81
     کیلوم
    -0.80
    Importing
    -0.79
     conhecer
    -0.79
    Accident
    -0.78
    POSITIVE LOGITS
     widespread
    1.02
     discrimination
    1.01
     severe
    0.98
     Instances
    0.97
     instances
    0.94
     rampant
    0.92
    instances
    0.90
     Hidup
    0.87
    عين
    0.87
    廣
    0.85
    Activations Density 0.052%

    No Known Activations