© 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. 130382
    Prev
    Next
    INDEX
    Explanations

    based on given information

    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
     camioneta
    -1.09
     ราคา
    -1.05
     oyun
    -1.04
     éven
    -1.02
     trimestre
    -1.02
     唯美
    -1.01
     autonome
    -0.99
    aneity
    -0.97
    ón
    -0.96
    ificado
    -0.96
    POSITIVE LOGITS
     known
    1.94
     know
    1.79
     based
    1.63
     previous
    1.52
     expected
    1.40
     predicted
    1.31
     information
    1.29
     likely
    1.28
     knows
    1.27
     knowledge
    1.22
    Activations Density 0.063%

    No Known Activations