© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103723
    Prev
    Next
    INDEX
    Explanations

    URLs with index.php

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

    This neuron detects the occurrence of the token “index,” as in URL or file‐path segments named “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_34/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
     sytu
    -0.84
    <0xF3>
    -0.82
     wonder
    -0.81
     listrik
    -0.81
    чает
    -0.76
     assistance
    -0.76
    addError
    -0.74
     opt
    -0.73
    uges
    -0.73
    sighs
    -0.72
    POSITIVE LOGITS
    index
    1.13
     index
    0.92
     assurent
    0.91
    php
    0.90
     php
    0.84
    upto
    0.79
    indexed
    0.79
    不高
    0.78
     précédentes
    0.77
     дешевле
    0.76
    Activations Density 0.016%

    No Known Activations