© 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. 64793
    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
    ecznie
    -1.05
    cended
    -1.05
     vás
    -1.02
    ּוֹ
    -1.01
     {}));
    -0.98
     komment
    -0.97
    וּ
    -0.96
     consulté
    -0.96
     vulgaires
    -0.96
    сери
    -0.94
    POSITIVE LOGITS
    oczes
    1.16
    POM
    1.05
     parfois
    0.98
     novamente
    0.94
     plainte
    0.93
     идеально
    0.93
     portefeuille
    0.93
    école
    0.91
     chall
    0.90
     getestet
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.