© 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. 85169
    Prev
    Next
    INDEX
    Explanations

    colons, hyphens, numbers, or parentheticals

    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
     what
    -1.43
    กับ
    -1.42
     there
    -1.41
    нией
    -1.38
     varför
    -1.29
     senaste
    -1.22
    følge
    -1.20
    Tetapi
    -1.18
     laatste
    -1.18
     Ý
    -1.17
    POSITIVE LOGITS
     again
    1.50
     then
    1.39
     his
    1.30
     up
    1.25
     either
    1.23
     their
    1.22
     Gelegenheit
    1.20
    諷
    1.20
    当時
    1.18
    認真
    1.18
    Activations Density 0.236%

    No Known Activations