© 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. 10-GEMMASCOPE-RES-131K
    7. 102916
    Prev
    Next
    INDEX
    Explanations

    one day

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

    The neuron is triggered by the phrase “one day,” i.e. it detects occurrences of “one day.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    🫕
    -1.96
    絝
    -1.95
     försö
    -1.93
    WOMAN
    -1.80
     votación
    -1.80
    昳
    -1.77
     всѣ
    -1.73
    probieren
    -1.73
    =<
    -1.72
     boî
    -1.71
    POSITIVE LOGITS
    (
    2.63
    )
    2.14
     «
    1.94
    in
    1.75
    ]
    1.59
     besonders
    1.59
     в
    1.48
    <em>
    1.48
     schon
    1.45
    كم
    1.45
    Activations Density 0.006%

    No Known Activations