© 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. 25631
    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
     amerik
    -1.15
     ]:
    -1.06
    ⤒
    -1.05
     Αρχ
    -1.05
     paj
    -1.02
    pä
    -1.02
     surla
    -1.02
     aja
    -1.02
     lanka
    -1.01
    %%%%%%%%%%
    -1.00
    POSITIVE LOGITS
    我們
    1.11
     and
    1.10
     bewertet
    0.99
     paliwa
    0.97
     skvě
    0.97
     unseres
    0.96
    itars
    0.95
    🩻
    0.95
    がありますが
    0.94
    有時
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.