© 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. 32821
    Prev
    Next
    INDEX
    Explanations

    web and android code snippets

    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
     You
    -0.96
    Instead
    -0.88
    umburg
    -0.85
    Good
    -0.85
    Everyone
    -0.84
    You
    -0.83
    Now
    -0.80
    :
    -0.79
     Reden
    -0.79
     causes
    -0.79
    POSITIVE LOGITS
     OnInit
    0.96
    стояние
    0.87
    rody
    0.85
    izza
    0.83
    ABEL
    0.79
     ambil
    0.79
    Jesmyn
    0.79
    ministerium
    0.79
     musicale
    0.79
     geli
    0.79
    Activations Density 0.010%

    No Known Activations