© 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. 145236
    Prev
    Next
    INDEX
    Explanations

    toilet paper

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

    standalone products, traditional defenses, core needs

    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
    in
    0.52
     display
    0.50
     composto
    0.50
     الي
    0.49
     composing
    0.49
    eters
    0.48
    ä
    0.46
     تأثير
    0.45
     vollständig
    0.45
     calendario
    0.44
    POSITIVE LOGITS
    ค้า
    0.52
     coerc
    0.51
    付けて
    0.48
    ጃ
    0.48
    スペック
    0.48
    घी
    0.47
    ਘ
    0.47
    借
    0.47
    کریاں
    0.47
    赎
    0.47
    Activations Density 0.001%

    No Known Activations