© 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. 57045
    Prev
    Next
    INDEX
    Explanations

    Gossip Girl

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    unhofer
    -0.80
    uct
    -0.77
     Mahmoud
    -0.74
    ,$_
    -0.74
    ndef
    -0.67
    DEG
    -0.67
     qualified
    -0.66
    ^+
    -0.66
    🪸
    -0.66
     कै
    -0.65
    POSITIVE LOGITS
     Gossip
    1.62
    Gossip
    1.37
     Blair
    1.09
     Waldorf
    1.04
     gossip
    1.02
    Blair
    0.98
    gossip
    0.93
     Serena
    0.90
    XOXO
    0.89
     XO
    0.86
    Activations Density 0.013%

    No Known Activations