© 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. 34-GEMMASCOPE-RES-131K
    7. 98578
    Prev
    Next
    INDEX
    Explanations

    interrogation mark

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

    The neuron is detecting very common, high‐frequency function words (e.g. short articles, prepositions, and similar stopwords).

    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
    Beneath
    -0.91
     considér
    -0.83
    Ὁ
    -0.83
     lopp
    -0.83
     joyeux
    -0.81
     mitte
    -0.80
     extremo
    -0.79
    Stellar
    -0.78
     Är
    -0.77
    ônes
    -0.76
    POSITIVE LOGITS
     nachos
    0.84
     abiertas
    0.83
    EPA
    0.80
     sauté
    0.79
     сооб
    0.77
    vni
    0.77
    interopRequire
    0.75
    equalsIgnoreCase
    0.75
    Locations
    0.75
     terse
    0.74
    Activations Density 0.029%

    No Known Activations