© 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. 80676
    Prev
    Next
    INDEX
    Explanations

    preguntas y código técnico

    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
     ведет
    -1.80
    S
    -1.63
    and
    -1.62
    <
    -1.59
    </sup>
    -1.59
    at
    -1.56
    -1.56
    #
    -1.53
     обладает
    -1.52
     crée
    -1.51
    POSITIVE LOGITS
    tonsoft
    1.86
     by
    1.62
    spender
    1.58
    oader
    1.57
    izate
    1.56
    ……。
    1.55
    龵
    1.55
    UIFont
    1.50
    ollectionView
    1.49
     Öffnen
    1.49
    Activations Density 0.006%

    No Known Activations