© 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. 10-GEMMASCOPE-RES-131K
    7. 47639
    Prev
    Next
    INDEX
    Explanations

    steady state

    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
     to
    -2.94
    ৢ
    -2.86
    ため
    -2.78
     Betrach
    -2.64
     i
    -2.56
     '
    -2.48
     TAKE
    -2.44
     dando
    -2.42
     następnie
    -2.42
     The
    -2.39
    POSITIVE LOGITS
     моя
    2.88
    ꯸
    2.80
    ･･
    2.75
    ～　
    2.69
    ．．
    2.66
    Despite
    2.64
    With
    2.59
    　　*
    2.59
    　　-
    2.52
    咝
    2.52
    Activations Density 0.002%

    No Known Activations