© 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. 66630
    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
     garner
    -1.14
    ;
    -1.03
     сказали
    -1.03
    旅館
    -0.99
     linked
    -0.98
    ńskiego
    -0.98
    :
    -0.98
     “
    -0.97
     there
    -0.97
     before
    -0.95
    POSITIVE LOGITS
     lettere
    1.13
     мое
    1.06
     }),
    1.06
     privé
    1.05
    ఽ
    1.03
    是多少
    1.02
    ᴇ
    1.02
    艄
    1.02
    ANCING
    1.02
    бус
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.