© 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. 15904
    Prev
    Next
    INDEX
    Explanations

    likeness and analogy

    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
     znale
    -0.88
     award
    -0.88
     mojej
    -0.87
     desejo
    -0.84
     sonho
    -0.84
     bleibt
    -0.80
    yczna
    -0.80
     вопроса
    -0.79
     ótimo
    -0.79
    arté
    -0.78
    POSITIVE LOGITS
     like
    2.70
     akin
    2.59
     similar
    2.28
    เหมือน
    2.17
     podob
    2.17
    Similar
    2.09
    类似
    2.05
     giống
    2.05
     analogous
    2.05
     comparable
    2.05
    Activations Density 0.263%

    No Known Activations