© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119856
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
     they
    -1.46
    ynek
    -1.38
    回目の
    -1.38
    tyimages
    -1.37
     on
    -1.30
    чите
    -1.30
    ФИ
    -1.30
    på
    -1.27
    quanto
    -1.26
    ⓒ
    -1.24
    POSITIVE LOGITS
    うーん
    1.51
     any
    1.37
    さてさて
    1.36
    私に
    1.34
    というわけで
    1.34
     conceito
    1.34
     mostrou
    1.34
    誰が
    1.34
     perguntou
    1.33
    そういえば
    1.32
    Activations Density 0.123%

    No Known Activations