© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 505
    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
     reiter
    -1.52
     magnificent
    -1.41
     mediocre
    -1.41
     alluring
    -1.41
     sumptuous
    -1.38
     intriguing
    -1.38
     delightful
    -1.36
     amazingly
    -1.35
     serene
    -1.35
     splendid
    -1.35
    POSITIVE LOGITS
     Those
    1.30
     with
    1.21
     provide
    1.19
     That
    1.16
    What
    1.15
    Many
    1.14
    Other
    1.13
     if
    1.10
     those
    1.08
    Before
    1.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.