© 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. 10-GEMMASCOPE-RES-131K
    7. 10465
    Prev
    Next
    INDEX
    Explanations

    special characters

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

    special symbols and emojis, particularly decorative bullets, arrows, and pictographic characters used for visual formatting.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on pictographic and decorative symbols (emojis, flag icons, bullets, arrows, and other non-text glyphs).

    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
     when
    -1.81
    ailangan
    -1.46
     that
    -1.46
     went
    -1.44
     aña
    -1.37
    我们就
    -1.34
     stalled
    -1.32
     überrascht
    -1.31
    已經
    -1.31
     succumbed
    -1.30
    POSITIVE LOGITS
    },
    1.67
     teori
    1.57
    ÁL
    1.56
    ']),
    1.55
    idlertid
    1.54
    蹰
    1.54
     komik
    1.52
    ’,
    1.52
     eksper
    1.51
    ⚋
    1.50
    Activations Density 0.009%

    No Known Activations