© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94082
    Prev
    Next
    INDEX
    Explanations

    footage of people appearing

    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
     will
    -1.15
     now
    -1.09
     that
    -1.02
     these
    -0.93
     since
    -0.91
     because
    -0.89
    getDriver
    -0.88
     meestal
    -0.85
    さんと
    -0.85
     thinks
    -0.82
    POSITIVE LOGITS
     filmed
    1.48
    seem
    1.46
     appears
    1.44
     видно
    1.43
     visible
    1.41
     Appears
    1.41
     φα
    1.41
    appears
    1.40
     footage
    1.39
     seconds
    1.36
    Activations Density 0.066%

    No Known Activations