© 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. 15849
    Prev
    Next
    INDEX
    Explanations

    introductions, disclaimers, or days

    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
    cleos
    -1.04
     ندار
    -1.00
    ネタバレ
    -0.96
    Rifer
    -0.96
    Ecotoxicity
    -0.96
     בז
    -0.95
    feira
    -0.93
    题材
    -0.93
    jazdu
    -0.92
     among
    -0.91
    POSITIVE LOGITS
     endings
    1.11
    fritt
    1.09
     my
    1.09
     ends
    1.05
    ,
    1.02
    <eos>
    1.01
    珦
    1.00
    lán
    1.00
     übrigens
    0.99
    anyaan
    0.98
    Activations Density 0.012%

    No Known Activations