© 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. 10-GEMMASCOPE-RES-131K
    7. 1833
    Prev
    Next
    INDEX
    Explanations

    eti, UTI, or Tacoma

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

    The neuron is keyed to the character sequence “eti,” strongly activating on tokens that begin or include “eti” (as in etiology/etiologic).

    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
     Of
    -3.17
    镠
    -3.13
     If
    -2.64
     использованием
    -2.59
    犼
    -2.53
    *
    -2.52
    TacToe
    -2.50
    
    -2.45
    缯
    -2.41
    ꔛ
    -2.36
    POSITIVE LOGITS
    d
    2.66
    
    2.53
    ↵
    2.48
    acterísticas
    2.38
    ꜆
    2.27
    ”-
    2.27
     wth
    2.27
    瓿
    2.25
     marvel
    2.22
    ”(
    2.22
    Activations Density 0.026%

    No Known Activations