© 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. 25335
    Prev
    Next
    INDEX
    Explanations

    given names and surnames

    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
     provide
    -1.13
     mereka
    -1.13
     themselves
    -1.13
     сами
    -1.13
    icace
    -1.09
    ansvar
    -1.09
     it
    -1.04
     αυτή
    -1.02
     they
    -1.01
     dió
    -1.00
    POSITIVE LOGITS
     his
    1.33
    lllllllll
    1.13
     которы
    1.11
    mination
    1.10
    addContainer
    1.09
     identity
    1.08
     surname
    1.08
    heds
    1.07
    ledad
    1.06
     militer
    1.05
    Activations Density 0.047%

    No Known Activations