© 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. 34-GEMMASCOPE-RES-131K
    7. 57600
    Prev
    Next
    INDEX
    Explanations

    dates containing slashes or dots

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

    The neuron fires strongly on sequences of digits and separators in header comments (like “on 06/01/14”), i.e. date‐style numeric 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_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
     companies
    -0.88
    適量
    -0.81
    修復
    -0.81
     relevant
    -0.81
     this
    -0.79
    crimination
    -0.79
    riendo
    -0.78
    etsu
    -0.77
    をチェック
    -0.75
    sspiel
    -0.75
    POSITIVE LOGITS
     counsels
    0.84
    sans
    0.83
     Setelah
    0.81
     Vanity
    0.79
    쉘
    0.78
    颞
    0.76
    isticated
    0.75
     Manor
    0.75
    CHANNELS
    0.75
    rade
    0.74
    Activations Density 0.024%

    No Known Activations