© 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. 175885
    Prev
    Next
    INDEX
    Explanations

    royal names and relationships

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

    modal verbs indicating necessity

    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
     عين
    0.47
    нача
    0.46
    ق
    0.46
    ي
    0.46
    ر
    0.45
    အောင်
    0.45
    حال
    0.45
     قالب
    0.45
    ال
    0.45
     советы
    0.45
    POSITIVE LOGITS
     बिक
    0.45
     正規
    0.44
    /${
    0.44
     protes
    0.44
    ng
    0.43
     ἐ
    0.43
     ket
    0.42
     Voter
    0.42
     Regulation
    0.42
     미국
    0.42
    Activations Density 0.000%

    No Known Activations