© 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. 234957
    Prev
    Next
    INDEX
    Explanations

    hotels, maintain, low

    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
    囁
    0.43
     Hương
    0.42
     Rhys
    0.42
     dịp
    0.41
     হত্য
    0.40
     invites
    0.40
    ς
    0.40
    本
    0.39
    ブログ
    0.39
    িকে
    0.38
    POSITIVE LOGITS
     veditabbo
    0.53
     восем
    0.48
    쯜
    0.47
     первое
    0.46
     велосипе
    0.46
    摈
    0.46
     pedibus
    0.46
     первый
    0.46
    <unused682>
    0.46
     שנים
    0.45
    Activations Density 0.001%

    No Known Activations