© 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. 16396
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
     koncentr
    -1.06
    Nguyễn
    -1.05
    もう
    -0.94
     fok
    -0.93
    ням
    -0.93
     alkohol
    -0.93
     Depends
    -0.90
     zdol
    -0.90
    掬
    -0.89
     keram
    -0.88
    POSITIVE LOGITS
     so
    1.26
     quindi
    0.98
     Therefore
    0.98
     therefore
    0.97
    化した
    0.96
     więc
    0.94
    obacz
    0.93
     därför
    0.92
     Viertel
    0.92
     harmony
    0.90
    Activations Density 0.001%

    No Known Activations