© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 131070
    Prev
    Next
    INDEX
    Explanations

    waste, rage, kitchen, initiated, neoplasms

    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
     identify
    -1.15
     achieve
    -1.12
     generate
    -1.08
     change
    -1.07
     diminish
    -1.05
     increase
    -1.05
     provide
    -1.05
     enhance
    -1.03
     Almost
    -1.02
     protect
    -1.01
    POSITIVE LOGITS
    etting
    1.29
    ⁵
    1.27
    otropy
    1.27
    mètres
    1.23
    <!--<
    1.23
     afl
    1.18
    ItemView
    1.17
     {
    
    
    1.17
    *<
    1.17
    )$;
    1.16
    Activations Density 0.125%

    No Known Activations