© 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. 84600
    Prev
    Next
    INDEX
    Explanations

    self adhesive

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

    non-english words and symbols

    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
     важ
    0.44
     RADIOACTIVE
    0.44
    льм
    0.42
     গুরুত্বপূর্ণ
    0.42
    最重要的
    0.42
    ޚ
    0.41
    ността
    0.41
     भला
    0.41
    াপন্ন
    0.39
    重要的
    0.39
    POSITIVE LOGITS
     diesem
    0.50
     acest
    0.50
     sondern
    0.49
     avec
    0.48
     utilisent
    0.48
     Kons
    0.47
    ਟ
    0.46
    schein
    0.45
     ovom
    0.45
     Architektur
    0.45
    Activations Density 0.004%

    No Known Activations