© 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. 149475
    Prev
    Next
    INDEX
    Explanations

    pros, advantages, essay topics

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

    with explanations or justifications

    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
    но
    0.49
    associate
    0.48
    shows
    0.45
    СО
    0.44
    сения
    0.44
    ↵↵
    0.44
     -,
    0.44
    Associate
    0.44
    шня
    0.43
    5
    0.43
    POSITIVE LOGITS
     राजप
    0.50
     magnificence
    0.49
     ilyen
    0.49
    微软雅黑
    0.47
     így
    0.46
    ंदरे
    0.46
     perhitungan
    0.45
    १८६
    0.45
     trataro
    0.45
    য়াছে
    0.44
    Activations Density 0.000%

    No Known Activations