© 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. 10-GEMMASCOPE-RES-131K
    7. 70994
    Prev
    Next
    INDEX
    Explanations

    tilde and backend

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

    The neuron strongly activates on occurrences of the tilde character (the “~” marker).

    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
     delineate
    -2.55
    んびり
    -2.50
    ing
    -2.47
    n
    -2.44
    ↵
    -2.44
    昞
    -2.33
     venture
    -2.33
    栁
    -2.31
    s
    -2.31
     incluidas
    -2.23
    POSITIVE LOGITS
    鄚
    2.78
     artisti
    2.61
     damen
    2.41
    ной
    2.38
     russo
    2.36
     miesię
    2.34
     menyen
    2.31
     اهم
    2.23
     favoriser
    2.20
     sekunder
    2.20
    Activations Density 0.003%

    No Known Activations