© 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. 10-GEMMASCOPE-RES-131K
    7. 61016
    Prev
    Next
    INDEX
    Explanations

    reinforcement learning or deep learning

    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_10/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
    loyed
    -1.06
    洗衣
    -1.00
     fratelli
    -0.99
     not
    -0.98
    anej
    -0.97
     pathlib
    -0.97
    了口气
    -0.94
    licopter
    -0.94
    Kommentare
    -0.93
    kelijk
    -0.93
    POSITIVE LOGITS
    rália
    1.38
    蟜
    1.21
     urbanos
    1.20
    siyah
    1.19
     with
    1.16
    pection
    1.15
     abstrato
    1.13
     erzielen
    1.13
     conducts
    1.08
    nch
    1.08
    Activations Density 0.043%

    No Known Activations