© 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. 22-GEMMASCOPE-RES-131K
    7. 28044
    Prev
    Next
    INDEX
    Explanations

    first names followed by surnames

    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_22/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
    y
    -3.00
     The
    -2.89
     или
    -2.63
     '
    -2.59
    ra
    -2.52
     atau
    -2.45
    \
    -2.41
     With
    -2.25
    1
    -2.23
     необхідно
    -2.22
    POSITIVE LOGITS
     Hinsicht
    2.59
    椟
    2.53
    .
    2.50
     để
    2.38
    鼋
    2.31
    猹
    2.28
     INFORMACIÓN
    2.27
    ℣
    2.25
     mélange
    2.25
    齎
    2.20
    Activations Density 0.093%

    No Known Activations