© 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. 5654
    Prev
    Next
    INDEX
    Explanations

    to be or consist of

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

    french words starting with ch

    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
     මහ
    0.39
    砓
    0.39
     approbation
    0.37
    三个
    0.37
     üçüncü
    0.37
    学生的
    0.37
    ເພດ
    0.37
    LOLL
    0.37
     પોલીસ
    0.36
    牫
    0.36
    POSITIVE LOGITS
    Primera
    0.42
    orden
    0.40
    명이
    0.38
    bergement
    0.37
    rana
    0.36
    pera
    0.36
     Sydney
    0.36
    Sydney
    0.36
     מע
    0.35
     G
    0.34
    Activations Density 0.018%

    No Known Activations