© 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. 22-GEMMASCOPE-RES-131K
    7. 35623
    Prev
    Next
    INDEX
    Explanations

    torial concepts: torque, moment, angular momentum

    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_22/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
    kennen
    -1.20
     hè
    -1.19
     direitos
    -1.16
     quí
    -1.16
     negócios
    -1.16
     人間
    -1.14
     nimmer
    -1.14
    ·
    -1.13
     heo
    -1.12
    FILL
    -1.10
    POSITIVE LOGITS
    1
    1.23
     llegamos
    1.19
     this
    1.13
    <bos>
    1.11
     bolster
    1.07
     makeshift
    1.06
     at
    1.02
    dyti
    1.01
     antiquated
    1.01
     son
    1.00
    Activations Density 0.012%

    No Known Activations