© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49648
    Prev
    Next
    INDEX
    Explanations

    purpose of or to

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

    The neuron responds to hyphenated numerical descriptors (e.g. “two-part,” “three-fold”).

    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
     полови
    -0.74
    半年
    -0.71
     viên
    -0.71
    osit
    -0.71
     одного
    -0.69
     ключ
    -0.68
     одному
    -0.68
     key
    -0.68
     дале
    -0.67
     По
    -0.67
    POSITIVE LOGITS
     twofold
    4.09
     threefold
    3.58
     manifold
    2.66
    fold
    2.13
    tw
    2.06
    manifold
    2.06
     fold
    1.88
     tw
    1.82
     manifolds
    1.77
    ofold
    1.71
    Activations Density 0.129%

    No Known Activations