© 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. 64957
    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
     én
    -1.00
    ꜥ
    -0.97
    DESCRIPTOR
    -0.93
    THING
    -0.93
     théâtre
    -0.91
    hver
    -0.91
     dichter
    -0.91
    蚰
    -0.90
     besonder
    -0.89
     fantasma
    -0.88
    POSITIVE LOGITS
     dokładnie
    1.09
    tilor
    0.98
     erhoben
    0.98
     mantis
    0.94
    enske
    0.91
    We
    0.88
     nostre
    0.88
    這裡
    0.87
     nuestros
    0.87
     sovra
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.