© 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. 130296
    Prev
    Next
    INDEX
    Explanations

    first name and surname

    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
     itself
    -1.80
     its
    -1.69
     is
    -1.66
     beeind
    -1.40
     whereas
    -1.38
     już
    -1.37
     or
    -1.35
     satisfecho
    -1.31
    tahui
    -1.31
     bereits
    -1.31
    POSITIVE LOGITS
     jotka
    1.63
     fernando
    1.58
     andreas
    1.48
     felipe
    1.40
     pedro
    1.35
     antonio
    1.31
     sergio
    1.31
     francisco
    1.31
     rodrigo
    1.30
     straff
    1.30
    Activations Density 0.026%

    No Known Activations