© 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. 74572
    Prev
    Next
    INDEX
    Explanations

    symbols and foreign characters

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

    The neuron flags individual non-ASCII Unicode characters—i.e. isolated foreign‐script or special symbols rather than ordinary Latin 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
     embracing
    -2.17
     Before
    -2.09
     بسیار
    -2.05
    我的
    -2.03
    Surprisingly
    -1.98
     incessant
    -1.95
    Donativos
    -1.93
     venturing
    -1.93
     शुर
    -1.92
     unrelenting
    -1.90
    POSITIVE LOGITS
    ⚣
    2.84
    
    2.69
     wonderfully
    2.64
     exceptionally
    2.61
    𓁹
    2.59
     insanely
    2.53
     delightfully
    2.52
     ridiculously
    2.41
     renowned
    2.39
     amazingly
    2.36
    Activations Density 0.000%

    No Known Activations