© 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. 65725
    Prev
    Next
    INDEX
    Explanations

    specific 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
     horloge
    -1.77
    閖
    -1.59
     flotte
    -1.55
    ሾ
    -1.55
     paille
    -1.53
     salari
    -1.53
     géant
    -1.52
    illots
    -1.52
     Infór
    -1.52
     क्यों
    -1.52
    POSITIVE LOGITS
     it
    2.70
     our
    2.59
     by
    2.59
     my
    2.20
     so
    2.14
     through
    2.00
     not
    1.98
     at
    1.88
     each
    1.82
     will
    1.81
    Activations Density 1.448%

    No Known Activations