© 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. 22-GEMMASCOPE-RES-131K
    7. 98390
    Prev
    Next
    INDEX
    Explanations

    technical / code delimiters

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

    This neuron is picking up on code/markup punctuation (e.g. angle-brackets, slashes, backslashes, dashes, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     only
    -1.05
    ว่า
    -0.97
     хоть
    -0.94
    com
    -0.94
    そんな
    -0.92
     appartement
    -0.91
    LAHOMA
    -0.91
     Following
    -0.87
     episodio
    -0.87
    PasswordEncoder
    -0.86
    POSITIVE LOGITS
     wrze
    1.23
    كويكب
    1.20
    andafter
    1.14
    なんですよ
    1.13
    久し
    1.13
     willen
    1.10
     prohibido
    1.09
     escuro
    1.05
     colgar
    1.05
     škoda
    1.05
    Activations Density 0.086%

    No Known Activations