© 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. 22-GEMMASCOPE-RES-131K
    7. 72921
    Prev
    Next
    INDEX
    Explanations

    variable/property names

    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_22/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
    urally
    -1.05
    ableness
    -1.03
    ！(
    -1.02
    ifiers
    -1.00
    !$
    -0.97
     tirage
    -0.97
    aneity
    -0.94
    naires
    -0.94
    hirts
    -0.94
    ocrats
    -0.93
    POSITIVE LOGITS
    くれない
    1.04
     responded
    0.98
    の方も
    0.96
     tutt
    0.96
    方も
    0.93
    人也
    0.92
     accueille
    0.91
    躺
    0.91
    ごちそう
    0.90
     ragion
    0.89
    Activations Density 0.006%

    No Known Activations