© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70943
    Prev
    Next
    INDEX
    Explanations

    persistence and effort

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

    This neuron fires on occurrences of the character sequence “perse” (e.g. in words like perseverance, persevered, Perseids, or Persepolis).

    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
    Zubereitung
    -2.78
    菝
    -2.42
     governo
    -2.38
    拊
    -2.27
     inoxydable
    -2.20
    魮
    -2.19
    इटम
    -2.16
     We
    -2.16
    л
    -2.16
    Schweiz
    -2.14
    POSITIVE LOGITS
    s
    2.95
    ;
    
    2.89
    n
    2.34
    "]);
    
    2.20
    We
    2.17
    ):
    2.17
    th
    2.17
     and
    2.11
    </i>
    2.09
    적으로
    2.09
    Activations Density 0.001%

    No Known Activations