© 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. 55491
    Prev
    Next
    INDEX
    Explanations

    specific nouns after determiners

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

    person who

    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
    𝗧
    0.52
    Таким
    0.52
     असता
    0.50
    𝗡
    0.50
    منت
    0.49
    нуу
    0.49
    PackageReference
    0.49
    Decl
    0.47
    Pyrazole
    0.47
    Revolution
    0.46
    POSITIVE LOGITS
     yield
    0.53
    。
    0.52
     gon
    0.50
     j
    0.49
     default
    0.49
     grom
    0.49
     brakes
    0.47
     registrations
    0.47
     reload
    0.47
     nape
    0.46
    Activations Density 0.000%

    No Known Activations