© 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. 47148
    Prev
    Next
    INDEX
    Explanations

    named Inge, purchased Annie’s

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

    danger and recommendations

    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
     periodically
    0.43
    ,
    0.42
     améliorer
    0.41
     milioane
    0.41
     olim
    0.40
    的最佳
    0.39
     occasionally
    0.39
     milioni
    0.39
     ater
    0.39
     individually
    0.38
    POSITIVE LOGITS
     нет
    0.46
     পোশাক
    0.46
    炰
    0.46
    enfant
    0.44
     చేశాడు
    0.44
    有点
    0.43
     आक्रोश
    0.43
    ೀನ
    0.43
    脐
    0.43
     करता
    0.42
    Activations Density 0.000%

    No Known Activations