© 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. 158393
    Prev
    Next
    INDEX
    Explanations

    located

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

    atomic mass

    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
    徴
    0.52
    नल
    0.50
    來源
    0.46
    ின
    0.45
    יות
    0.45
    Arq
    0.45
     prawdzi
    0.44
    ያው
    0.44
    號
    0.44
     istraž
    0.44
    POSITIVE LOGITS
     divis
    0.42
    astrophe
    0.40
     مسئلے
    0.39
     lets
    0.39
     جانا
    0.38
    veless
    0.38
     มั้ย
    0.38
    আমিন
    0.38
    芜
    0.38
     non
    0.38
    Activations Density 0.000%

    No Known Activations