© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81500
    Prev
    Next
    INDEX
    Explanations

    comparison to thresholds

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

    The neuron strongly responds to numeric tokens denoting quantitative values or measurements (e.g. multi‐digit numbers).

    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
     (~
    -1.19
     slightly
    -1.14
    slightly
    -1.10
    Slightly
    -0.96
     Slightly
    -0.91
    少し
    -0.89
     約
    -0.85
     салат
    -0.85
    درب
    -0.84
    約
    -0.84
    POSITIVE LOGITS
     between
    1.70
     less
    1.52
     more
    1.23
     pomiędzy
    1.12
     over
    1.09
     above
    1.07
     více
    1.03
     below
    1.00
     greater
    1.00
     under
    0.98
    Activations Density 0.098%

    No Known Activations