© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16921
    Prev
    Next
    INDEX
    Explanations

    repetitive sequences of digits and symbols

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

    repeated characters and elements

    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
    शिक्षा
    0.37
    ၆
    0.36
    वीण
    0.36
     pièces
    0.35
    शिक्
    0.35
     intervalles
    0.35
    ائیو
    0.35
    isho
    0.34
    anns
    0.34
     morti
    0.34
    POSITIVE LOGITS
     Sparkling
    0.39
    これから
    0.38
     всего
    0.37
     気
    0.37
    々
    0.37
    嶄
    0.37
     همه
    0.36
     والت
    0.36
    や
    0.36
     Před
    0.35
    Activations Density 0.013%

    No Known Activations