© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64697
    Prev
    Next
    INDEX
    Explanations

    legislation and its passage

    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
     käyttää
    -0.92
     olivat
    -0.84
     arrangements
    -0.84
     dispersal
    -0.82
    ものは
    -0.82
    ie
    -0.81
     entschieden
    -0.81
    消失了
    -0.80
    ik
    -0.80
    ("'"
    -0.79
    POSITIVE LOGITS
     passed
    1.74
     would
    1.48
    passed
    1.25
     Passed
    1.24
     proposed
    1.18
     PASS
    1.16
    Passed
    1.11
     authored
    1.11
     died
    1.05
     propos
    1.05
    Activations Density 0.037%

    No Known Activations