© 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. 131765
    Prev
    Next
    INDEX
    Explanations

    wage limit, then now, first, Cody, badly, midwives, music, questions

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

    purchase, especially, aligned, augmentation, less, businesses

    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
    ние
    0.52
    summar
    0.52
    Change
    0.51
    Pract
    0.51
    ²)
    0.50
    reviews
    0.49
    Deep
    0.48
    Actually
    0.48
    Tax
    0.47
    Ine
    0.47
    POSITIVE LOGITS
     manga
    0.52
     onion
    0.50
     haunting
    0.49
     astral
    0.47
     manger
    0.46
     jPanel
    0.45
     prevista
    0.45
     항
    0.45
     maniak
    0.45
     jung
    0.44
    Activations Density 0.000%

    No Known Activations