© 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. 22-GEMMASCOPE-RES-131K
    4. 54283
    Prev
    Next
    INDEX
    Explanations

    symbols and closing characters

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

    The neuron responds to isolated symbol tokens—especially HTML entities, punctuation marks, and icon‐like characters (e.g. “>”, “×”, “✖”, “☰”, 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
     such
    -1.49
     said
    -1.32
     a
    -1.31
    ↵↵
    -1.30
     these
    -1.28
     that
    -1.28
    :
    -1.24
     on
    -1.22
     those
    -1.22
     who
    -1.18
    POSITIVE LOGITS
     terminer
    1.48
     empêcher
    1.46
     bascul
    1.41
    ╯
    1.38
     varier
    1.36
     offrir
    1.34
     fermer
    1.32
    excellents
    1.31
     applau
    1.30
    焌
    1.30
    Activations Density 0.001%

    No Known Activations