© 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. 479
    Prev
    Next
    INDEX
    Explanations

    date ranges and durations

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

    The neuron strongly activates on numeric tokens (digits and numbers), especially those appearing in dates or other numeric expressions.

    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
    ົ
    -0.95
     appear
    -0.89
    offsetWidth
    -0.89
     MONTHS
    -0.86
    })();
    -0.85
    か月
    -0.84
     AssemblyVersion
    -0.84
     months
    -0.83
    cm
    -0.83
    Months
    -0.82
    POSITIVE LOGITS
    Kav
    0.92
    也不用
    0.81
    Deacti
    0.75
    Dani
    0.72
    NoStop
    0.72
    Queues
    0.71
    三天
    0.71
    Databases
    0.71
     ASI
    0.69
     gider
    0.69
    Activations Density 0.021%

    No Known Activations