© 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. 102965
    Prev
    Next
    INDEX
    Explanations

    XML tag names and following attributes/identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    XML/XSL markup syntax and structured code elements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     on
    -1.50
    amp
    -1.37
    罠
    -1.35
     to
    -1.34
    すぎる
    -1.26
    垍
    -1.24
     malheure
    -1.23
     通り
    -1.22
    上記の
    -1.20
    跛
    -1.20
    POSITIVE LOGITS
     my
    1.63
     Edición
    1.57
    ↵
    1.56
     motocicleta
    1.45
     motocic
    1.41
     Opiniones
    1.41
    er
    1.40
     Reglas
    1.38
     wszystkie
    1.37
     sorprender
    1.35
    Activations Density 0.029%

    No Known Activations