© 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. 39452
    Prev
    Next
    INDEX
    Explanations

    selected vehicle components

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

    prime factorization and division

    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
    白
    0.44
     লিখিত
    0.40
    轻
    0.40
    流
    0.39
    ushchev
    0.39
     প্রচারণা
    0.38
    LLOW
    0.38
    gewater
    0.38
     পারিবারিক
    0.38
    绑
    0.37
    POSITIVE LOGITS
     zum
    0.47
     seleccionado
    0.47
     seleccion
    0.45
     sporty
    0.44
     selecion
    0.44
     ausge
    0.42
     selected
    0.42
    amba
    0.42
     arac
    0.42
     chosen
    0.42
    Activations Density 0.011%

    No Known Activations