© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79824
    Prev
    Next
    INDEX
    Explanations

    mathematical arithmetic series

    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_22/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
     excluir
    -1.32
     azeite
    -1.13
     detecta
    -1.08
    ͛
    -1.05
     administrativa
    -1.05
    genuine
    -1.05
     vasos
    -1.04
     pessoa
    -1.04
     motyw
    -1.04
    ָל
    -1.01
    POSITIVE LOGITS
     inclusief
    1.01
    ierungs
    0.97
    PlayerPrefs
    0.95
    ナメント
    0.93
     this
    0.91
     premise
    0.91
    throwable
    0.91
    ଶ
    0.90
     within
    0.88
    パーティ
    0.88
    Activations Density 0.226%

    No Known Activations