© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9908
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

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

    The neuron specializes in spotting uppercase technical acronyms (e.g. AFM) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鵟
    -3.02
    
    -2.94
    姈
    -2.88
    闿
    -2.63
     intitulée
    -2.59
    ЛОВ
    -2.58
    ⎔
    -2.58
     Quels
    -2.56
     Détails
    -2.56
    
    -2.55
    POSITIVE LOGITS
    '
    3.39
    m
    2.83
    </strong>
    2.81
    ll
    2.66
    is
    2.64
    C
    2.64
    so
    2.58
    g
    2.45
     ‎
    2.42
    of
    2.39
    Activations Density 0.035%

    No Known Activations