© 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. 34-GEMMASCOPE-RES-131K
    7. 115626
    Prev
    Next
    INDEX
    Explanations

    SQL INSERT statements

    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_34/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
     even
    -1.31
     on
    -1.16
     out
    -1.13
    Even
    -1.11
     tailored
    -1.09
     Taking
    -1.05
     by
    -1.04
     best
    -1.03
     not
    -1.02
     Nearly
    -1.02
    POSITIVE LOGITS
     opulent
    1.03
    ilding
    1.03
     flamboyant
    1.02
    がありますが
    0.99
    Kun
    0.99
    
    0.99
     trám
    0.98
     BEAUTIFUL
    0.97
     magnific
    0.96
     faciliter
    0.96
    Activations Density 0.000%

    No Known Activations