© 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. 66001
    Prev
    Next
    INDEX
    Explanations

    word stems and endings

    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
     of
    -1.34
     to
    -1.13
     vė
    -1.08
     maž
    -1.07
     сериал
    -1.06
     сериала
    -1.05
     esetén
    -1.05
    СЫ
    -1.04
    помо
    -1.02
     gydy
    -1.02
    POSITIVE LOGITS
     and
    2.66
     tramonto
    1.24
    tubers
    1.06
    </em>
    1.05
    …]
    1.05
    Aceite
    1.03
    opie
    1.03
    懌
    1.01
    artig
    1.01
    vidades
    1.01
    Activations Density 0.076%

    No Known Activations