© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127670
    Prev
    Next
    INDEX
    Explanations

    creation date and user

    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
    Negative Logits
    B
    -1.25
     tecnolog
    -1.02
    TestingModule
    -1.02
    личный
    -1.00
    ailangan
    -1.00
    X
    -1.00
    *
    -0.99
    H
    -0.96
    ὺς
    -0.94
    ：……
    -0.94
    POSITIVE LOGITS
    슴
    1.09
    OrUpdate
    1.08
    ensä
    1.07
    merkungen
    1.06
     freshmen
    1.05
    初始
    1.04
     date
    1.02
    钝
    1.02
     pétrole
    1.00
    ieros
    0.99
    Activations Density 0.012%

    No Known Activations