© 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. 22-GEMMASCOPE-RES-131K
    7. 25754
    Prev
    Next
    INDEX
    Explanations

    symbols followed by punctuation

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

    This neuron activates on single‐letter (or short) mathematical variable names appearing in formulas or LaTeX math expressions.

    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
     and
    -1.37
     második
    -1.15
     जबकि
    -1.09
     accesorio
    -1.09
     nadru
    -1.07
     impresora
    -1.06
    agod
    -1.05
     samoz
    -1.02
    mazda
    -1.02
     anillo
    -1.02
    POSITIVE LOGITS
    k
    1.09
    B
    1.02
    ic
    1.02
    ge
    0.97
    l
    0.96
    F
    0.94
    p
    0.93
    M
    0.92
    Fr
    0.92
     they
    0.91
    Activations Density 0.030%

    No Known Activations