© 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. 15260
    Prev
    Next
    INDEX
    Explanations

    single or sole entity

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    atto
    -0.84
    mbres
    -0.84
    roves
    -0.83
     confusion
    -0.83
    FromNib
    -0.82
    itorio
    -0.80
    Coordonnées
    -0.80
    这个时候
    -0.80
     pain
    -0.79
    uvres
    -0.79
    POSITIVE LOGITS
     monopoly
    1.29
     single
    1.28
     monopol
    1.24
     sole
    1.23
    mono
    1.21
    Sole
    1.18
     solely
    1.17
    单
    1.16
     lone
    1.16
     only
    1.16
    Activations Density 0.075%

    No Known Activations