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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2819
    Prev
    Next
    INDEX
    Explanations

    improving or rewriting text for clarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     THEY
    0.82
     ಅವನು
    0.73
     bactéries
    0.72
    These
    0.70
    They
    0.70
     ความ
    0.68
    😗
    0.68
     volgens
    0.66
    ﻬ
    0.66
     คำ
    0.64
    POSITIVE LOGITS
     facilities
    0.73
     campus
    0.69
     site
    0.67
     Midlands
    0.67
     Dorset
    0.66
     Yorkshire
    0.66
     premises
    0.66
     cottages
    0.65
     Belfast
    0.65
    施設
    0.65
    Activations Density 0.189%

    No Known Activations