© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58369
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    得上
    -1.45
    だろうか
    -1.38
     or
    -1.33
    StoryboardSegue
    -1.25
     just
    -1.25
     unequivocal
    -1.23
     Following
    -1.23
     During
    -1.20
     Saltar
    -1.16
     parseFrom
    -1.16
    POSITIVE LOGITS
     şirket
    1.45
    一起去
    1.30
     reunião
    1.28
    瘆
    1.26
    ᕮ
    1.24
    ︕
    1.21
    こんなに
    1.20
    謌
    1.20
    </h3>
    1.19
     annet
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.