© 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. 3212
    Prev
    Next
    INDEX
    Explanations

    digital media, heritage, technologies

    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
     internet
    -1.11
     Qualitäts
    -0.91
     hacker
    -0.83
     control
    -0.82
     Internet
    -0.82
     IT
    -0.81
     cyber
    -0.78
     ciber
    -0.78
     Bitcoin
    -0.78
    ularis
    -0.77
    POSITIVE LOGITS
    divide
    0.84
     ethn
    0.84
     Horatio
    0.82
     mediates
    0.81
    واقع
    0.81
     squa
    0.79
     mediator
    0.79
     mediating
    0.78
    Excluded
    0.78
     fluency
    0.78
    Activations Density 0.042%

    No Known Activations