© 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. 22-GEMMASCOPE-RES-131K
    7. 27422
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with indices

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

    The neuron fires on mathematical variable tokens carrying subscripts or indices (e.g. a_i, I_n, k).

    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
     дів
    -1.40
     it
    -1.28
    ところに
    -1.27
     пам
    -1.27
    ほうがいい
    -1.24
     поши
    -1.23
    為に
    -1.23
     потрі
    -1.23
    沢山
    -1.22
    上記の
    -1.21
    POSITIVE LOGITS
    を
    1.56
    がある
    1.56
    と
    1.35
    同志
    1.31
    などが
    1.31
    骉
    1.24
     is
    1.24
    などを
    1.22
     produisons
    1.22
     kanad
    1.20
    Activations Density 0.035%

    No Known Activations