© 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. 92965
    Prev
    Next
    INDEX
    Explanations

    definite article followed by noun

    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
    rably
    -1.08
     chrétien
    -1.08
    ographique
    -1.02
     ANOTHER
    -0.96
     adelante
    -0.96
    oglobin
    -0.96
     pertemuan
    -0.95
    pods
    -0.95
    remain
    -0.95
     představ
    -0.94
    POSITIVE LOGITS
     biggest
    1.86
     lack
    1.73
     only
    1.66
     absence
    1.51
     latest
    1.49
     inability
    1.48
     overall
    1.48
     entire
    1.43
     also
    1.39
     same
    1.38
    Activations Density 0.042%

    No Known Activations