© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41843
    Prev
    Next
    INDEX
    Explanations

    remember me, reusable

    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
    </strong>
    -1.23
    Sedangkan
    -1.09
    UNG
    -1.06
    ↵
    -1.05
    艰难
    -1.05
     kim
    -1.02
    вге
    -1.02
     парке
    -1.02
     ato
    -1.01
     arch
    -1.00
    POSITIVE LOGITS
    豋
    1.47
    ără
    1.36
    if
    1.30
     sconto
    1.30
    。”
    1.27
    At
    1.23
    with
    1.20
    You
    1.18
    ÑOS
    1.16
    which
    1.15
    Activations Density 0.061%

    No Known Activations