© 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. 13455
    Prev
    Next
    INDEX
    Explanations

    Philip Nelson, Q:, Welcome to

    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
     their
    -1.27
     fantástica
    -1.22
    ってる
    -1.12
     рік
    -1.11
     naudoti
    -1.09
     or
    -1.02
     baratas
    -1.02
     skvě
    -1.00
     romántica
    -0.99
    excellents
    -0.98
    POSITIVE LOGITS
     .............
    1.28
    aneity
    1.27
     ...............
    1.25
    ...............
    1.22
     ............
    1.20
     .........
    1.19
     ...........
    1.18
     ........
    1.18
     ..........
    1.17
    zielle
    1.13
    Activations Density 0.002%

    No Known Activations