© 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. 22-GEMMASCOPE-RES-131K
    7. 26458
    Prev
    Next
    INDEX
    Explanations

    index.html path

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

    This neuron activates on tokens referring to file or path names (especially “index”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     zrobić
    -1.09
    aussi
    -0.98
     hulle
    -0.96
     length
    -0.95
     моих
    -0.93
     parecen
    -0.93
     ťaž
    -0.92
     diciendo
    -0.91
     each
    -0.91
    之前
    -0.90
    POSITIVE LOGITS
    њу
    1.18
     сумка
    1.18
    闈
    1.08
     leaflets
    1.06
     muro
    1.05
    ―――
    1.02
    senza
    1.02
     apto
    1.01
    优秀的
    0.99
     pintar
    0.99
    Activations Density 0.012%

    No Known Activations