© 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. 93723
    Prev
    Next
    INDEX
    Explanations

    darkness and dark

    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
    ストラリア
    -0.70
     Iba
    -0.65
     idolat
    -0.65
    五日
    -0.65
    が見えて
    -0.63
    doctrine
    -0.63
     zing
    -0.62
    pé
    -0.62
    yssey
    -0.61
     [_
    -0.60
    POSITIVE LOGITS
     darkness
    6.28
     dark
    5.63
    dark
    4.84
     Darkness
    4.47
    darkness
    4.38
    Darkness
    4.25
    Dark
    4.22
     darkened
    3.97
    黑暗
    3.94
     Dark
    3.92
    Activations Density 0.067%

    No Known Activations