© 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. 28255
    Prev
    Next
    INDEX
    Explanations

    list of items

    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
     formid
    -1.13
    蠵
    -1.09
    
    -1.09
    
    -1.06
    ⚫
    -1.06
    künfte
    -1.05
     افتراض
    -1.05
    皤
    -1.02
    锃
    -1.02
    💢
    -1.02
    POSITIVE LOGITS
     other
    1.55
     such
    1.43
     additional
    1.25
     child
    1.24
     children
    1.16
     offers
    1.10
     events
    1.09
     q
    1.09
     more
    1.06
     like
    1.05
    Activations Density 0.011%

    No Known Activations