© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85766
    Prev
    Next
    INDEX
    Explanations

    words ending in ento or enta

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

    This neuron activates on occurrences of the letter sequence “enta” (or very close variants) within words.

    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
    er
    -3.66
    ti
    -2.73
    ?”
    -2.61
    ਃ
    -2.59
    L
    -2.47
     When
    -2.42
     Historically
    -2.36
    籥
    -2.34
    y
    -2.34
     prosegu
    -2.34
    POSITIVE LOGITS
    趼
    2.83
     啦
    2.69
    砹
    2.64
     sebagainya
    2.31
    喽
    2.28
    这几
    2.25
    л
    2.25
    že
    2.23
    HomeAsUpEnabled
    2.20
    
    2.19
    Activations Density 0.039%

    No Known Activations