© 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. 200652
    Prev
    Next
    INDEX
    Explanations

    foreign characters or mixed language

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

    mythology, oral traditions, and sections

    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
    Э
    0.52
     Э
    0.45
    Эта
    0.45
    ر
    0.44
    Une
    0.43
    Ма
    0.43
    El
    0.42
    formin
    0.42
    Uw
    0.42
    Το
    0.42
    POSITIVE LOGITS
     ব্যক্ত
    0.51
    
    0.50
     künstler
    0.47
     Zust
    0.47
     底
    0.46
     တို့
    0.45
    𝗌
    0.44
     ಕೈ
    0.44
    personen
    0.44
     省
    0.43
    Activations Density 0.000%

    No Known Activations