© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104697
    Prev
    Next
    INDEX
    Explanations

    numbers followed by years

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

    The neuron selectively responds to LaTeX “tilde” tokens (e.g. the “~” used in chemical‐formula subscript notation).

    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
    C
    -2.42
    s
    -2.41
    i
    -2.41
     gets
    -2.30
     gave
    -2.22
     gives
    -2.19
     showed
    -2.16
     solely
    -2.09
     actually
    -2.09
     could
    -2.09
    POSITIVE LOGITS
    
    2.41
    )};
    2.23
     tunik
    2.19
    
    2.16
     estándares
    2.16
    欤
    2.09
    ఙ
    2.08
    狨
    2.06
     jednej
    2.03
    
    2.00
    Activations Density 0.035%

    No Known Activations