© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 5571
    Prev
    Next
    INDEX
    Explanations

    between two entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     депозит
    0.46
     uninsured
    0.42
    //}
    0.41
     Actualmente
    0.40
    ಿಯು
    0.40
     CLIENTI
    0.39
     allowances
    0.37
    辣椒
    0.37
    objeto
    0.37
    ungannya
    0.37
    POSITIVE LOGITS
     Between
    0.47
    㡀
    0.45
    ሕ
    0.42
    の実
    0.40
     byl
    0.40
     வைர
    0.39
     Fernseh
    0.39
    Between
    0.39
    ierung
    0.39
     perché
    0.39
    Activations Density 0.003%

    No Known Activations