© 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. 28132
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     their
    -1.38
     as
    -1.21
     many
    -1.17
     helps
    -1.13
     mostly
    -1.13
     only
    -1.11
     just
    -1.11
     not
    -1.11
     more
    -1.10
     almost
    -1.10
    POSITIVE LOGITS
    might
    1.13
    therefore
    1.09
     Dinas
    1.09
    ಇ
    1.08
    llac
    1.07
    ⩴
    1.07
     poë
    1.02
    Daha
    1.02
     geene
    1.02
    okat
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.