© 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-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 950
    Prev
    Next
    INDEX
    Explanations

    logically contradicting statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    চারের
    1.36
     bénéf
    1.30
    াস্ত
    1.24
     Verbre
    1.21
    concrete
    1.18
    値
    1.18
    aktual
    1.18
    čního
    1.17
    ški
    1.17
    প্তি
    1.15
    POSITIVE LOGITS
     họp
    1.84
     trại
    1.79
     vui
    1.74
     सुबह
    1.73
    騁
    1.71
     sông
    1.71
    arlene
    1.70
     nghĩ
    1.65
    䒷
    1.63
     halved
    1.61
    Activations Density 0.000%

    No Known Activations