© 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. 12548
    Prev
    Next
    INDEX
    Explanations

    often describes concepts

    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
     жы
    -1.16
    bt
    -1.16
     which
    -1.10
     sogar
    -1.10
     видит
    -1.09
    ves
    -1.07
    igraphy
    -1.02
     bude
    -1.00
     МВД
    -0.98
    rop
    -0.96
    POSITIVE LOGITS
    Often
    1.19
    żenie
    1.12
     often
    1.08
    ejec
    1.03
     Often
    1.03
     or
    1.01
    éte
    1.01
     cofre
    1.00
     føl
    0.99
     scegliere
    0.99
    Activations Density 0.416%

    No Known Activations