© 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. 77279
    Prev
    Next
    INDEX
    Explanations

    best pal, attractive fares

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

    wet dreams, common practices

    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
    ạng
    0.52
    Chapter
    0.51
    창
    0.49
    채
    0.49
     (
    0.48
    ל
    0.48
    يد
    0.47
    ար
    0.47
    ма
    0.46
    <0xE3>
    0.46
    POSITIVE LOGITS
    ጋገብ
    0.54
    izienz
    0.51
     হেম
    0.48
    তাহাকে
    0.47
     CheckException
    0.47
     υψη
    0.45
     সেক্ষেত্রে
    0.45
     जरी
    0.45
     تقسیم
    0.44
     aprendido
    0.43
    Activations Density 0.000%

    No Known Activations