© 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. 60521
    Prev
    Next
    INDEX
    Explanations

    predicting nouns after articles

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

    specific protocols and requirements

    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
     language
    0.49
     our
    0.49
    anges
    0.47
     a
    0.46
    obby
    0.45
     languages
    0.45
    asa
    0.45
    utan
    0.45
    nu
    0.44
     discipline
    0.44
    POSITIVE LOGITS
     عشر
    0.54
    วิ่ง
    0.49
    e
    0.49
    }+\
    0.48
    i
    0.48
     pierwszym
    0.48
     ursprüng
    0.46
    🚜
    0.46
    xAxis
    0.46
    يلي
    0.46
    Activations Density 0.000%

    No Known Activations