© 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. 65698
    Prev
    Next
    INDEX
    Explanations

    sunlight and moonlight effects

    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
    渇
    -0.90
     oscuro
    -0.89
     magnetite
    -0.82
    liflower
    -0.80
     бампер
    -0.80
    alice
    -0.79
    readFileSync
    -0.79
    ̗
    -0.79
    Liên
    -0.78
    existsSync
    -0.77
    POSITIVE LOGITS
     filtered
    1.42
     through
    1.38
     filtering
    1.32
    filtered
    1.19
     filters
    1.15
    beam
    1.14
     illuminating
    1.13
     penetrating
    1.12
     hitting
    1.12
     filter
    1.12
    Activations Density 0.028%

    No Known Activations