© 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. 79613
    Prev
    Next
    INDEX
    Explanations

    HTML tags and citations

    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
     for
    -1.64
     noticeable
    -1.63
     despite
    -1.51
     throughout
    -1.48
     have
    -1.45
     regardless
    -1.44
     Grecia
    -1.44
     including
    -1.44
    </i>
    -1.41
     their
    -1.41
    POSITIVE LOGITS
    )
    1.50
     ww
    1.39
    ឵
    1.34
     erinner
    1.33
     kvě
    1.32
     álcool
    1.28
     mecán
    1.28
     debacle
    1.27
     INTERNATIONAL
    1.26
     květ
    1.26
    Activations Density 0.008%

    No Known Activations