© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129160
    Prev
    Next
    INDEX
    Explanations

    URLs and code paths

    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
     immediately
    -1.21
     essentially
    -1.18
     appropriately
    -1.16
     Give
    -1.14
     not
    -1.13
     Get
    -1.12
     definitely
    -1.10
     rigorous
    -1.10
     destroying
    -1.10
     this
    -1.09
    POSITIVE LOGITS
     neces
    1.14
     Atención
    1.13
     vœux
    1.12
     '\\
    1.10
     acheter
    1.05
     vélo
    1.03
     faciliter
    1.03
     Boletín
    1.02
     Badan
    1.02
     plafon
    1.02
    Activations Density 0.037%

    No Known Activations