© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 356
    Prev
    Next
    INDEX
    Explanations

    communication about entities

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

    names and closings

    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_16k_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
     segmental
    0.25
     pathways
    0.24
     extractive
    0.24
    
    0.22
     EBITDA
    0.22
    quantile
    0.22
    imetric
    0.22
     transversal
    0.22
     rentable
    0.22
     actionable
    0.21
    POSITIVE LOGITS
     replied
    0.32
     aka
    0.30
     (@
    0.30
     dijo
    0.30
     fratello
    0.30
     написал
    0.29
     scrive
    0.29
     schrieb
    0.28
     wrote
    0.28
     skrev
    0.28
    Activations Density 0.859%

    No Known Activations