© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65842
    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
    ky
    -1.15
    l
    -1.15
    }
    -1.12
    i
    -1.12
    ous
    -1.03
    硕
    -0.99
    j
    -0.98
    1
    -0.98
    v
    -0.96
     $
    -0.95
    POSITIVE LOGITS
    olde
    1.31
     салат
    1.20
    `
    1.17
     FÜR
    1.15
     pleaf
    1.09
    chambre
    1.09
     RECIPES
    1.09
     fhort
    1.08
     menghubungi
    1.05
    chakra
    1.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.