© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40909
    Prev
    Next
    INDEX
    Explanations

    proper nouns 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
    UnknownFieldSet
    -1.39
    licante
    -1.34
     serons
    -1.33
    儼
    -1.30
    牙齿
    -1.30
    やってる
    -1.30
    ナの
    -1.30
     zpě
    -1.28
     memutus
    -1.27
    nitř
    -1.26
    POSITIVE LOGITS
     other
    1.91
     of
    1.80
     same
    1.67
     abbraccio
    1.58
     Finally
    1.58
     chiusura
    1.57
    ↵↵↵
    1.52
     preghiera
    1.52
     etc
    1.52
     ragazza
    1.51
    Activations Density 0.055%

    No Known Activations