© 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. 10-GEMMASCOPE-RES-131K
    7. 71439
    Prev
    Next
    INDEX
    Explanations

    parenthesized expressions

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

    The neuron activates on numeric tokens (numbers and numeric expressions, including floats).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -2.56
     
    -1.73
     “
    -1.70
     part
    -1.61
    ですか
    -1.46
    assemblée
    -1.46
    )$\\
    -1.44
    忖
    -1.42
     допомогою
    -1.41
     Перейти
    -1.39
    POSITIVE LOGITS
     this
    1.73
     météoro
    1.73
     ataupun
    1.73
    8
    1.70
    あっという間に
    1.58
     insanity
    1.56
     atau
    1.56
     месе
    1.54
     végétal
    1.54
    5
    1.53
    Activations Density 0.001%

    No Known Activations