© 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. 7049
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

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

    This neuron responds to short all-caps letter sequences (like “AT,” “FT,” “PT”) that mark technical abbreviations (e.g. microcontroller model names or protein/gene acronyms).

    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
    いい
    -0.90
    Especificación
    -0.87
    hits
    -0.84
     Boeh
    -0.84
    hil
    -0.84
    something
    -0.83
    Elaboración
    -0.82
    Tecnología
    -0.81
    Volker
    -0.81
     misteriosa
    -0.80
    POSITIVE LOGITS
    жден
    0.94
     Above
    0.85
    ass
    0.84
    Ahead
    0.81
    lh
    0.81
    öt
    0.81
    bt
    0.81
    Above
    0.79
    oses
    0.78
    MotionEvent
    0.78
    Activations Density 0.070%

    No Known Activations