© 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. 11597
    Prev
    Next
    INDEX
    Explanations

    IBAN

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

    prefix `a` or `da`

    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
    فيذ
    0.45
    Understand
    0.39
    中国人
    0.38
     changer
    0.36
     guessed
    0.36
     signaler
    0.36
    訾
    0.36
     glances
    0.36
    ندوق
    0.35
    Finland
    0.35
    POSITIVE LOGITS
    iffen
    0.38
    ICAGO
    0.37
    🐼
    0.37
                                  
    0.37
    🎃
    0.36
    atsiya
    0.36
    imak
    0.35
    ụn
    0.35
     goi
    0.35
     Grove
    0.35
    Activations Density 0.028%

    No Known Activations