© 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. 19873
    Prev
    Next
    INDEX
    Explanations

    structured data blocks

    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
    _
    -1.50
     a
    -1.34
    〇〇
    -1.30
     даже
    -1.27
     丈
    -1.23
     своей
    -1.21
     exaggerated
    -1.20
     encantó
    -1.17
    -
    -1.16
    甚至
    -1.14
    POSITIVE LOGITS
     Gegensatz
    1.52
     soggiorno
    1.51
     meravigli
    1.48
    桄
    1.30
     jesteśmy
    1.30
     adatta
    1.28
     segredo
    1.27
     modificare
    1.27
    babwe
    1.26
     листья
    1.26
    Activations Density 0.005%

    No Known Activations