© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65830
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    This neuron specializes in spotting log‐style timestamps (numeric date/time strings) in error/stack‐trace output.

    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
     tulis
    -1.23
    Ори
    -1.14
    estacks
    -1.13
    Город
    -1.13
     palav
    -1.11
     viera
    -1.10
     astu
    -1.08
    geç
    -1.05
     biblia
    -1.05
     pasaran
    -1.05
    POSITIVE LOGITS
    aka
    1.16
    chi
    1.09
    ay
    1.09
    em
    1.06
    on
    1.06
    ot
    1.03
    et
    1.03
    oy
    1.02
    am
    1.02
    ha
    1.00
    Activations Density 0.010%

    No Known Activations