© 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. 111095
    Prev
    Next
    INDEX
    Explanations

    tunnel vision and technology

    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
    Иван
    -0.95
     avocat
    -0.94
     Popup
    -0.94
    Tomato
    -0.91
    hộp
    -0.91
    тератур
    -0.90
     salada
    -0.90
     canina
    -0.88
     poule
    -0.88
    쥰
    -0.88
    POSITIVE LOGITS
     vision
    1.32
    led
    1.20
     leading
    1.16
    vision
    1.13
     between
    1.13
     connecting
    0.98
    ways
    0.98
     Vision
    0.97
     systems
    0.96
     linking
    0.96
    Activations Density 0.027%

    No Known Activations