© 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. 36071
    Prev
    Next
    INDEX
    Explanations

    “ when

    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
    我們
    -1.35
     потім
    -1.34
     zapato
    -1.28
    著者
    -1.22
     coloris
    -1.18
    我们在
    -1.16
    　『
    -1.15
    んだろう
    -1.13
     our
    -1.12
    我们
    -1.09
    POSITIVE LOGITS
     said
    1.52
     molti
    1.36
     also
    1.32
     alcune
    1.28
     it
    1.28
     instead
    1.27
     Wednesday
    1.27
    だが
    1.23
     molte
    1.22
     however
    1.21
    Activations Density 0.001%

    No Known Activations