© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3313
    Prev
    Next
    INDEX
    Explanations

    web page redirects

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

    The neuron strongly activates on occurrences of “redirect” (including forms like “Redirecting”) in the text.

    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
    返品
    -0.94
    鯷
    -0.92
     المعيارى
    -0.88
    揽
    -0.85
    ↵↵
    -0.85
    ついて
    -0.85
     advancing
    -0.84
     noiva
    -0.84
     devolved
    -0.84
     angel
    -0.83
    POSITIVE LOGITS
     to
    1.64
    ToAction
    1.04
     właścic
    0.98
    FINED
    0.97
    至
    0.94
     back
    0.94
     redi
    0.93
    rable
    0.91
    bait
    0.91
     レッド
    0.91
    Activations Density 0.010%

    No Known Activations