© 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. 61830
    Prev
    Next
    INDEX
    Explanations

    Explained

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

    fits or suits your style

    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
    ness
    0.46
     بالس
    0.45
    !}
    0.44
    t
    0.44
    at
    0.43
    i
    0.43
    nes
    0.42
     itin
    0.42
     oxford
    0.42
     nes
    0.42
    POSITIVE LOGITS
    敵
    0.50
     schrift
    0.48
    該
    0.46
     इनवर्स
    0.46
    呆
    0.46
     Objetivo
    0.46
     doel
    0.45
    屬於
    0.45
    夢
    0.45
    インチ
    0.45
    Activations Density 0.000%

    No Known Activations