© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35204
    Prev
    Next
    INDEX
    Explanations

    database id and column

    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
     profundas
    -0.88
     while
    -0.85
     problem
    -0.84
     strong
    -0.83
     work
    -0.83
     Issue
    -0.81
     improved
    -0.81
     actuales
    -0.80
    Heading
    -0.80
     happy
    -0.80
    POSITIVE LOGITS
     TECHNOLOGIES
    0.95
     Diakses
    0.92
     anzuzeigen
    0.90
    榊
    0.88
     tecnología
    0.87
    ständen
    0.86
    嚀
    0.86
     eum
    0.85
     Appellants
    0.84
     ><
    0.84
    Activations Density 0.012%

    No Known Activations