© 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. 64938
    Prev
    Next
    INDEX
    Explanations

    annual or yearly frequency

    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
     high
    -1.16
     any
    -1.10
     that
    -1.05
     new
    -1.04
     via
    -1.03
     about
    -1.02
     or
    -1.01
    餐廳
    -1.00
     systems
    -0.99
    );
    -0.98
    POSITIVE LOGITS
     annually
    1.73
    每年
    1.69
     yearly
    1.66
     annual
    1.48
     previous
    1.29
    毎回
    1.29
     предыду
    1.28
    Chaque
    1.27
    เคย
    1.27
     سنوات
    1.27
    Activations Density 0.098%

    No Known Activations