© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79141
    Prev
    Next
    INDEX
    Explanations

    gossipy bloggers and scandals

    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
     BBC
    -0.91
    UNEP
    -0.90
    tifact
    -0.90
    IDENCE
    -0.90
     Lös
    -0.85
    PBS
    -0.84
     PBS
    -0.84
     sync
    -0.81
     NPR
    -0.80
    bbc
    -0.78
    POSITIVE LOGITS
     gossip
    1.45
    Gossip
    1.17
     blogger
    1.17
     Anonymous
    1.16
     Gossip
    1.16
     anonymous
    1.15
    Anonymous
    1.13
     gossi
    1.10
    gossip
    1.07
     bloggers
    0.95
    Activations Density 0.095%

    No Known Activations