© 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. 98625
    Prev
    Next
    INDEX
    Explanations

    file sharing links and services

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

    The main thing this neuron does is spot URL fragments and download‐link tokens (e.g. parts of mega.nz, dropbox.com, and similar file-sharing URLs).

    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
     catalogo
    -0.85
     caratteri
    -0.78
    שי
    -0.75
    Function
    -0.70
     Förder
    -0.70
     unchanging
    -0.70
     particolari
    -0.69
     Compound
    -0.68
     relax
    -0.68
    电话
    -0.68
    POSITIVE LOGITS
     Dropbox
    1.12
     shared
    1.04
     sharing
    1.02
     condiv
    0.92
     partage
    0.92
    shared
    0.90
     OneDrive
    0.90
     share
    0.88
    Dropbox
    0.87
    share
    0.84
    Activations Density 0.016%

    No Known Activations