© 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. 27064
    Prev
    Next
    INDEX
    Explanations

    specific time periods

    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
     first
    -1.26
    ịn
    -1.04
     an
    -1.01
    先
    -1.01
    Referències
    -0.98
     itulah
    -0.96
    最初
    -0.96
    幾
    -0.96
    首先
    -0.96
    iramente
    -0.96
    POSITIVE LOGITS
     year
    1.81
     report
    1.59
    year
    1.52
     årets
    1.47
     yearly
    1.28
     annual
    1.24
     בשנת
    1.20
     annually
    1.19
     året
    1.17
    année
    1.16
    Activations Density 0.033%

    No Known Activations