© 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. 34-GEMMASCOPE-RES-131K
    7. 78545
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and concepts

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

    The neuron fires on specialized high-level mathematical terminology—especially algebraic‐geometry terms like “coherent,” “modules,” “Mumford,” “lemma,” and “red book.”

    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
    assertArray
    -0.82
    ceedings
    -0.82
    urers
    -0.80
    }`,
    -0.79
    Wired
    -0.78
    enguaje
    -0.77
     Сти
    -0.74
     деревья
    -0.73
     vertices
    -0.72
    WriteByte
    -0.71
    POSITIVE LOGITS
     coherent
    0.84
    mathscr
    0.83
     lpg
    0.76
     sheaf
    0.75
     péro
    0.75
     flas
    0.74
    Kilde
    0.72
     pils
    0.71
     Moons
    0.69
     müßte
    0.69
    Activations Density 0.028%

    No Known Activations