© 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. 128518
    Prev
    Next
    INDEX
    Explanations

    names and initials in citations

    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
     ご
    -0.95
    的身影
    -0.93
     insist
    -0.90
    ご予約
    -0.90
     descended
    -0.89
     berlina
    -0.88
     dichotomy
    -0.88
     outskirts
    -0.86
     destroy
    -0.85
     began
    -0.84
    POSITIVE LOGITS
    ritsar
    1.07
    ⿻
    1.03
     предлагает
    1.02
     efekty
    1.01
    anmar
    1.00
     collè
    0.99
     ciep
    0.98
    khu
    0.98
     fuir
    0.96
     cán
    0.96
    Activations Density 0.012%

    No Known Activations