© 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. 77966
    Prev
    Next
    INDEX
    Explanations

    was/were found or observed

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

    The neuron is detecting numeric measurements and quantitative values (numbers) in scientific or technical text.

    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
    QPushButton
    -0.88
    ))=\
    -0.84
    Included
    -0.81
    احبه
    -0.81
     RADIO
    -0.78
     HEARING
    -0.77
     представления
    -0.77
    灵气
    -0.77
    )=\
    -0.76
     NIGHT
    -0.76
    POSITIVE LOGITS
     observed
    5.31
    observed
    3.66
     found
    3.64
     Observed
    3.48
     observe
    3.41
    Observed
    3.28
     observes
    2.91
     seen
    2.80
     witnessed
    2.75
     recorded
    2.61
    Activations Density 0.311%

    No Known Activations