© 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. 22-GEMMASCOPE-RES-131K
    4. 104711
    Prev
    Next
    INDEX
    Explanations

    qualifications or estimates

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

    The main thing this neuron does is detect numeric values and quantitative specification language (e.g. figures, estimates, measurements, dates) in the 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_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
     it
    -1.15
    jublj
    -1.03
    ₃
    -1.03
     dõi
    -1.03
     الشرطة
    -0.99
    .*")]
    -0.98
    numsp
    -0.97
    స్త
    -0.96
    gilet
    -0.96
    บริการ
    -0.96
    POSITIVE LOGITS
     from
    1.46
    あくまで
    1.45
     based
    1.18
     которыми
    1.17
     merely
    1.17
     for
    1.10
     are
    1.05
    そのため
    1.01
    あく
    1.00
    atillo
    0.99
    Activations Density 0.035%

    No Known Activations