© 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. 54407
    Prev
    Next
    INDEX
    Explanations

    deferring actions

    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
     remarkably
    -1.44
     proveniente
    -1.40
     puramente
    -1.38
     nowy
    -1.36
     predominantly
    -1.35
    
    -1.34
     nombreuses
    -1.34
     largely
    -1.33
     emporter
    -1.32
     mange
    -1.31
    POSITIVE LOGITS
     on
    1.64
     but
    1.62
     at
    1.59
     or
    1.59
    !
    1.41
     after
    1.38
     in
    1.34
     taking
    1.32
    It
    1.31
     during
    1.31
    Activations Density 0.001%

    No Known Activations