© 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. 78791
    Prev
    Next
    INDEX
    Explanations

    academic citations and journal titles

    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
    Detective
    -0.84
    irdre
    -0.80
    okości
    -0.80
     Vgl
    -0.77
    intercept
    -0.75
    mediately
    -0.74
    detective
    -0.72
    ností
    -0.72
    ádza
    -0.71
    ⬘
    -0.70
    POSITIVE LOGITS
     Journal
    1.09
     Computers
    1.09
     presented
    0.98
    presented
    0.96
    Journal
    0.96
     JOURNAL
    0.88
     journal
    0.88
     accepted
    0.85
     soumis
    0.84
     IEEE
    0.83
    Activations Density 0.031%

    No Known Activations