© 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. 128512
    Prev
    Next
    INDEX
    Explanations

    equations to solve for variables

    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
    前進
    -0.78
    kkers
    -0.77
     douleur
    -0.76
    mergeFrom
    -0.75
     réelle
    -0.75
     Percentage
    -0.74
     tâche
    -0.73
    dodge
    -0.72
     Observations
    -0.72
     even
    -0.71
    POSITIVE LOGITS
     sosok
    0.99
     gemeenten
    0.91
    CLP
    0.91
    UrlHelper
    0.82
     државе
    0.82
    อน
    0.82
     rangkaian
    0.81
    Omar
    0.81
     Spanyol
    0.81
    ünk
    0.80
    Activations Density 0.050%

    No Known Activations