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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98546
    Prev
    Next
    INDEX
    Explanations

    events, taught, private, lots

    np_acts-logits-general · gemini-2.5-flash-lite

    torrent, industrial, nature, media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     registers
    0.54
    处
    0.52
    综合
    0.48
    显著
    0.48
    开放
    0.47
    改变
    0.46
     aggregation
    0.46
    桥
    0.45
    坝
    0.45
    袄
    0.45
    POSITIVE LOGITS
     sprawie
    0.54
    メディア
    0.49
    QD
    0.48
     スニーカー
    0.48
    தமிழ
    0.47
     スリム
    0.47
    Heart
    0.47
    Nada
    0.47
     ます
    0.47
    MediaPlayer
    0.46
    Activations Density 0.000%

    No Known Activations