© 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. 13108
    Prev
    Next
    INDEX
    Explanations

    multiples of variables preceded by operators

    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
     brutal
    -1.06
     even
    -1.00
     is
    -0.96
     before
    -0.94
     を
    -0.93
     has
    -0.93
    が
    -0.90
     la
    -0.87
     does
    -0.87
     vocal
    -0.87
    POSITIVE LOGITS
     accompag
    1.21
    decided
    1.20
    every
    1.09
    amazing
    1.09
     adresses
    1.08
    everyone
    1.06
     slou
    1.06
     poud
    1.05
     choses
    1.05
     BEEN
    1.03
    Activations Density 0.018%

    No Known Activations