© 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. 143687
    Prev
    Next
    INDEX
    Explanations

    this forum

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

    elegant syntax

    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
    ı
    0.55
     liht
    0.52
     regole
    0.50
     üld
    0.50
    è
    0.49
     Salon
    0.48
    ā
    0.47
     semplice
    0.47
     decidir
    0.46
    á
    0.46
    POSITIVE LOGITS
    斑
    0.52
    КУ
    0.45
    脈
    0.45
    ﹀
    0.45
    智慧
    0.44
    修士
    0.44
    츰
    0.44
     mimics
    0.43
    ⑸
    0.43
     curvy
    0.42
    Activations Density 0.001%

    No Known Activations