© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80792
    Prev
    Next
    INDEX
    Explanations

    Czech and Slovak characters

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

    This neuron detects non-ASCII characters—especially letters with diacritics or Cyrillic letters.

    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
    PEZ
    -2.83
    翦
    -2.75
    忆
    -2.61
    経由
    -2.58
    </strong>
    -2.56
    Ꮋ
    -2.42
    逦
    -2.41
    玬
    -2.36
    ญี่ป
    -2.31
    渙
    -2.31
    POSITIVE LOGITS
    4
    4.59
    6
    4.47
    2
    4.31
    7
    4.25
    '
    4.19
    3
    4.06
    1
    3.98
    5
    3.91
    8
    3.73
    9
    3.28
    Activations Density 0.007%

    No Known Activations