© 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. 47011
    Prev
    Next
    INDEX
    Explanations

    MechWarrior universe

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

    The neuron fires on pieces of web addresses (e.g. “http,” “://,” domain name parts, “.,” “com,” “/”), i.e. it detects URLs.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    nę
    -0.80
    pora
    -0.79
     strlen
    -0.77
    ʋ
    -0.77
     borrower
    -0.77
     cortisol
    -0.77
    ATED
    -0.76
    stappen
    -0.74
     Luffy
    -0.74
     midterm
    -0.74
    POSITIVE LOGITS
     Mech
    1.23
    Mech
    1.13
     Liao
    1.05
     tonnage
    0.90
     mech
    0.85
    mech
    0.83
     Clan
    0.83
    Dav
    0.82
     Inner
    0.82
    iphery
    0.81
    Activations Density 0.012%

    No Known Activations