© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9709
    Prev
    Next
    INDEX
    Explanations

    forwarded by slash

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

    The neuron is detecting date/time expressions—numbers (and their slash separators) used in dates and timestamps.

    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
    家は
    -1.56
    }});
    -1.43
     in
    -1.41
    家が
    -1.41
    ॠ
    -1.38
     kimia
    -1.38
     ефек
    -1.37
    EdgeInsets
    -1.36
    猻
    -1.33
    𓄹
    -1.33
    POSITIVE LOGITS
    ,
    1.55
    G
    1.34
    2
    1.34
    na
    1.27
     sechs
    1.25
    l
    1.22
    al
    1.22
     kleinere
    1.21
    w
    1.21
    ne
    1.20
    Activations Density 0.016%

    No Known Activations