© 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. 106981
    Prev
    Next
    INDEX
    Explanations

    passing through barriers

    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
     McFadden
    -0.85
     sprigs
    -0.83
     snippets
    -0.79
    iper
    -0.79
    jidad
    -0.75
     wipers
    -0.75
    Inverse
    -0.75
     Clips
    -0.75
     Cure
    -0.74
     snippet
    -0.74
    POSITIVE LOGITS
     walls
    1.46
     wall
    1.27
     drywall
    1.16
     thick
    1.05
     flesh
    1.02
     fabric
    1.00
     Decke
    0.99
     epidermis
    0.99
     defences
    0.95
     through
    0.94
    Activations Density 0.071%

    No Known Activations