© 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. 16217
    Prev
    Next
    INDEX
    Explanations

    eigenvalues and eigenvectors

    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
     parece
    -0.95
    ߯
    -0.93
     KENT
    -0.92
     krach
    -0.92
    itives
    -0.91
     WALT
    -0.88
     COLE
    -0.87
    стями
    -0.87
    OLY
    -0.85
     relâche
    -0.85
    POSITIVE LOGITS
     people
    0.91
     принадлежа
    0.91
     it
    0.83
     index
    0.82
     corresponding
    0.81
     choose
    0.79
    níků
    0.79
    culado
    0.78
     Erscheinung
    0.76
     freilich
    0.74
    Activations Density 0.020%

    No Known Activations