© 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. 27552
    Prev
    Next
    INDEX
    Explanations

    months and years

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags temporal reference tokens—especially words like “this” and “next” and numeral tokens used to indicate years, percentages, or time periods.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    *?
    -0.97
    ⁉
    -0.96
     Rasulullah
    -0.95
    :?
    -0.93
     プレミアム
    -0.92
    
    -0.91
     pérd
    -0.91
    ROZ
    -0.91
     Termine
    -0.88
    😥
    -0.88
    POSITIVE LOGITS
     April
    1.28
     year
    1.26
     August
    1.22
     July
    1.20
     June
    1.19
     onwards
    1.10
     March
    1.06
     December
    1.05
     October
    0.98
     February
    0.97
    Activations Density 0.107%

    No Known Activations