© 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. 127588
    Prev
    Next
    INDEX
    Explanations

    introducing speech or examples

    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
     Frühjahr
    -2.63
     "-
    -2.63
     ("
    -2.58
     і
    -2.52
     $\
    -2.41
     "...
    -2.38
     "[
    -2.36
    
    -2.31
     "'
    -2.30
     Это
    -2.25
    POSITIVE LOGITS
    er
    3.05
    ti
    2.95
    “
    2.84
    ῞
    2.47
    你
    2.47
    是在
    2.23
     goodbye
    2.16
    缡
    2.14
    )
    2.14
     miraculous
    2.13
    Activations Density 0.032%

    No Known Activations