© 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. 65603
    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
     crescente
    -0.98
    Zubereitung
    -0.95
     wrestle
    -0.92
    🗯
    -0.88
     seinem
    -0.86
    Consequently
    -0.85
    機種
    -0.85
     बीच
    -0.84
     violenta
    -0.84
    Beschrijving
    -0.83
    POSITIVE LOGITS
     them
    1.00
     capucha
    0.87
    เคย
    0.84
    曾經
    0.84
     того
    0.84
     phường
    0.84
    寫
    0.82
     Treated
    0.80
     conformance
    0.80
    曾经
    0.80
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.