© 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. 31048
    Prev
    Next
    INDEX
    Explanations

    featured this week

    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
    journalist
    -0.91
     dominio
    -0.88
     criticised
    -0.83
     event
    -0.81
     journalists
    -0.81
     vaisselle
    -0.79
     reunion
    -0.79
     even
    -0.78
    estr
    -0.77
     خود
    -0.77
    POSITIVE LOGITS
     featured
    2.66
     spotlight
    2.19
    featured
    2.09
    Featured
    2.06
     feature
    2.06
    FEATURE
    1.91
    feature
    1.85
     Featured
    1.81
    spotlight
    1.63
     featuring
    1.59
    Activations Density 0.089%

    No Known Activations