© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95720
    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
     all
    -1.92
     their
    -1.73
     every
    -1.58
     with
    -1.54
     which
    -1.45
     some
    -1.45
     what
    -1.43
     over
    -1.37
     those
    -1.34
     ALL
    -1.32
    POSITIVE LOGITS
     asemenea
    1.71
    Hilsen
    1.61
     obicei
    1.45
    ţele
    1.40
    ਗ਼
    1.34
     COULD
    1.34
     appelés
    1.33
     streamlining
    1.32
     dieß
    1.32
     dilapidated
    1.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.