© 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. 68330
    Prev
    Next
    INDEX
    Explanations

    grand, early, assistant, sale

    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
     There
    -1.45
     creates
    -1.41
     reduces
    -1.38
     as
    -1.35
     one
    -1.34
     While
    -1.32
     what
    -1.31
     Also
    -1.30
     With
    -1.30
     more
    -1.30
    POSITIVE LOGITS
    trying
    1.41
     flamboyant
    1.36
    extremely
    1.36
    螃
    1.34
     ornate
    1.32
    completely
    1.28
     magnific
    1.28
    <bos>
    1.25
     demostr
    1.24
     Elegant
    1.22
    Activations Density 0.244%

    No Known Activations