© 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. 14981
    Prev
    Next
    INDEX
    Explanations

    numerical times of day

    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
    ounid
    -1.13
    cuencia
    -1.08
    autres
    -1.05
    態度
    -1.02
    や
    -1.00
    饅
    -0.99
    資本
    -0.98
     other
    -0.97
    生態
    -0.97
    品種
    -0.96
    POSITIVE LOGITS
     evening
    1.48
     afternoon
    1.33
     night
    1.25
     előtt
    1.20
     late
    1.12
     hours
    1.11
    ならではの
    1.11
     morning
    1.09
     
    1.09
    citations
    1.04
    Activations Density 0.022%

    No Known Activations