© 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. 33760
    Prev
    Next
    INDEX
    Explanations

    years and months

    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
    afterEach
    -0.88
    BufferedReader
    -0.87
    thargy
    -0.87
    rama
    -0.86
    perror
    -0.85
     preceding
    -0.82
     万
    -0.82
    enerbahçe
    -0.82
     unfamiliar
    -0.81
    щення
    -0.80
    POSITIVE LOGITS
     his
    1.12
     に関する
    0.94
     graisse
    0.81
    ellant
    0.79
     belangrijk
    0.78
     platy
    0.77
    ênio
    0.77
     pries
    0.75
    appartement
    0.75
     eerst
    0.75
    Activations Density 0.048%

    No Known Activations