© 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. 73385
    Prev
    Next
    INDEX
    Explanations

    Regents of the University

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

    The neuron activates on multi-letter uppercase sequences (acronyms/initialisms).

    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
    ون
    -2.77
    禤
    -2.42
    踽
    -2.41
    衪
    -2.39
    
    -2.33
    ized
    -2.31
     regards
    -2.23
     bustling
    -2.17
    s
    -2.16
     заканчи
    -2.09
    POSITIVE LOGITS
    逦
    3.16
    as
    2.28
     peluang
    2.22
    戗
    2.20
    骓
    2.20
    две
    2.11
    侂
    2.09
     What
    2.06
    an
    2.05
     sommige
    2.02
    Activations Density 0.014%

    No Known Activations