© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14887
    Prev
    Next
    INDEX
    Explanations

    occurring pairs of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incluyendo
    0.59
     incluindo
    0.49
    ┙
    0.47
    絊
    0.46
     zuerst
    0.44
     pierwsze
    0.44
     entrenamiento
    0.43
     endet
    0.43
     lahat
    0.43
     damals
    0.42
    POSITIVE LOGITS
     Modifications
    0.44
    မူ
    0.41
     modifying
    0.39
     असल्या
    0.39
    基于
    0.38
     законо
    0.38
    ଂ
    0.38
    Uno
    0.38
    ებისა
    0.38
    奇异
    0.38
    Activations Density 0.032%

    No Known Activations