© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111732
    Prev
    Next
    INDEX
    Explanations

    specific technical terms

    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_262k_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
    तो
    0.50
     DOI
    0.49
    is
    0.48
    هی
    0.48
    ो
    0.48
    in
    0.47
     support
    0.46
     business
    0.46
     DO
    0.46
    у
    0.46
    POSITIVE LOGITS
     sugars
    0.50
     carénés
    0.49
     anions
    0.46
     carbs
    0.45
     homologs
    0.45
     odors
    0.45
    liquidacion
    0.43
     cannabinoids
    0.43
    ଵ
    0.43
     anisot
    0.42
    Activations Density 0.002%

    No Known Activations