© 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. 246264
    Prev
    Next
    INDEX
    Explanations

    with systems and procedures

    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
     น้อย
    0.46
     বিন্দু
    0.44
     banyaknya
    0.44
    حديد
    0.42
    DIALOG
    0.40
    ὥ
    0.39
     increment
    0.39
    servlet
    0.39
    本项目
    0.39
    لے
    0.39
    POSITIVE LOGITS
     찬
    0.47
     स्वर्
    0.47
     samt
    0.45
     asociado
    0.44
     каран
    0.44
    nsan
    0.43
    os
    0.43
    ant
    0.43
     който
    0.43
     pessoal
    0.42
    Activations Density 0.001%

    No Known Activations