© 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. 66244
    Prev
    Next
    INDEX
    Explanations

    references specific brands/models

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

    The neuron is strongly activated by very common English function words (e.g. “from,” “the,” “is,” “of”).

    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
     Siemens
    -1.11
     Sony
    -1.09
     IBM
    -1.07
    Siemens
    -1.06
     Nike
    -1.03
     Bosch
    -1.03
     Nintendo
    -1.02
    Sony
    -0.98
     Canon
    -0.95
     Apple
    -0.93
    POSITIVE LOGITS
    风雨
    0.97
    쩡
    0.96
     BREAKING
    0.89
     axiom
    0.88
     spolup
    0.85
     crowdfunding
    0.85
     goi
    0.85
    ווי
    0.85
     configurações
    0.85
    unrecognized
    0.84
    Activations Density 0.096%

    No Known Activations