© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 59665
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by articles or demonstratives

    np_acts-logits-general · gemini-2.5-flash-lite

    lists of entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     معنی
    0.45
    causing
    0.44
    confirm
    0.43
     объяснить
    0.43
    nless
    0.42
     confirm
    0.41
    тна
    0.41
    ൽ
    0.39
     proizv
    0.39
     detriment
    0.39
    POSITIVE LOGITS
     പിന്നീ
    0.46
    ફે
    0.45
    。）
    0.43
     blockbuster
    0.43
     Verlauf
    0.42
     cartoons
    0.42
     সূরা
    0.41
     RPG
    0.41
     groupings
    0.40
    生活中
    0.40
    Activations Density 0.000%

    No Known Activations