© 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. 75318
    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
     siff
    -1.23
     informar
    -1.16
     Agosto
    -1.13
     leal
    -1.11
     bebe
    -1.11
     Siria
    -1.09
     sois
    -1.09
     ponte
    -1.08
     paj
    -1.07
     Grecia
    -1.07
    POSITIVE LOGITS
     but
    1.20
     gebunden
    1.09
    But
    1.04
     angebracht
    1.04
     adquis
    1.00
    âmara
    1.00
     gewähr
    1.00
    covite
    0.98
                             
    0.97
     umgeben
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.