© 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. 31410
    Prev
    Next
    INDEX
    Explanations

    mass shootings and school shooters

    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
    Torque
    -0.84
    રી
    -0.84
    üf
    -0.84
     torque
    -0.81
    ADRID
    -0.80
    més
    -0.75
     [''],
    -0.74
     insectes
    -0.74
     Exciting
    -0.74
    inkite
    -0.73
    POSITIVE LOGITS
     shooter
    2.56
     shooting
    2.50
     shootings
    2.27
     gunman
    2.23
     shooters
    2.08
    Shooting
    1.91
    shooting
    1.86
    shooter
    1.82
     Shooting
    1.80
     Shooter
    1.79
    Activations Density 0.054%

    No Known Activations