© 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. 34-GEMMASCOPE-RES-131K
    4. 81128
    Prev
    Next
    INDEX
    Explanations

    Q: questions

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

    The neuron fires on the colon punctuation character.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Perſ
    -1.06
     nejen
    -1.03
     catalán
    -1.02
     mostrando
    -1.00
    ˹
    -0.93
    HEMAT
    -0.92
     sooo
    -0.92
     masterful
    -0.91
     soooo
    -0.91
    tering
    -0.91
    POSITIVE LOGITS
     without
    1.32
     simply
    1.27
     just
    1.20
     просто
    1.19
     plain
    1.16
     default
    1.13
     other
    1.08
    default
    1.05
    Other
    1.05
     merely
    1.04
    Activations Density 0.031%

    No Known Activations