© 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. 83592
    Prev
    Next
    INDEX
    Explanations

    year-old victim

    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
     antioxidant
    -0.82
     STEIN
    -0.75
    Histogram
    -0.72
    Iya
    -0.71
     ico
    -0.70
     Mano
    -0.70
    colourful
    -0.70
    ඳ
    -0.68
     inkluder
    -0.68
    stl
    -0.68
    POSITIVE LOGITS
     physiotherapy
    0.89
    ас
    0.79
    จุด
    0.77
    intes
    0.77
    therapie
    0.76
     outrage
    0.75
    ẹn
    0.75
     lenient
    0.74
    υν
    0.74
     boiling
    0.74
    Activations Density 0.009%

    No Known Activations