© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84177
    Prev
    Next
    INDEX
    Explanations

    time of day

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

    The neuron is triggered by specific clock‐time expressions, especially times denoted with “am” or “pm.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     from
    -1.77
     of
    -1.19
     between
    -1.17
     like
    -1.14
    朝から
    -1.12
    C
    -1.10
    に行きました
    -1.05
    ab
    -1.05
    ><
    -1.03
     defined
    -1.02
    POSITIVE LOGITS
    sharp
    1.63
     sharp
    1.51
     EST
    1.27
     SHARP
    1.26
    harp
    1.23
     coû
    1.14
     PST
    1.11
     relâche
    1.11
     goû
    1.09
     作り方
    1.09
    Activations Density 0.017%

    No Known Activations