© 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. 34-GEMMASCOPE-RES-131K
    7. 3371
    Prev
    Next
    INDEX
    Explanations

    rest or remainder

    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_34/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
     değil
    -1.20
     löst
    -1.13
    だけは
    -1.13
     πρώ
    -1.12
     samtidigt
    -1.11
    ztő
    -1.10
    だけではなく
    -1.10
     pozor
    -1.10
    埭
    -1.09
    岙
    -1.08
    POSITIVE LOGITS
     either
    1.85
    either
    1.59
     restantes
    1.55
     entweder
    1.49
     остальных
    1.47
    Either
    1.47
     mostly
    1.42
    あとは
    1.42
     remainder
    1.41
     Either
    1.41
    Activations Density 0.049%

    No Known Activations