© 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. 216550
    Prev
    Next
    INDEX
    Explanations

    porcelain antiques

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

    specific lessons and groups

    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
    의
    0.53
     Audrey
    0.49
     categorias
    0.47
     cadeira
    0.47
     ل
    0.46
     dir
    0.46
     hava
    0.46
     manger
    0.44
     лет
    0.44
    Natalie
    0.44
    POSITIVE LOGITS
    犯
    0.52
    au
    0.50
    ведено
    0.49
    tar
    0.48
    盗
    0.48
    盜
    0.48
    ushu
    0.47
    fod
    0.47
    ва
    0.46
    ępuje
    0.46
    Activations Density 0.000%

    No Known Activations