© 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. 73479
    Prev
    Next
    INDEX
    Explanations

    Twin Earths

    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
     blusa
    -1.66
     blusas
    -1.66
     oxu
    -1.60
     plafon
    -1.54
     pantalon
    -1.53
    甃
    -1.52
     pistolet
    -1.52
    泐
    -1.52
     mikrofon
    -1.52
     aspek
    -1.52
    POSITIVE LOGITS
     D
    1.73
     one
    1.66
     M
    1.65
     an
    1.63
     new
    1.62
     h
    1.57
     H
    1.56
     in
    1.54
     with
    1.54
     as
    1.52
    Activations Density 0.001%

    No Known Activations