© 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. 204574
    Prev
    Next
    INDEX
    Explanations

    beginnings and changes

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

    expanding universe

    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
     যেহেতু
    0.47
    ेत
    0.45
    рез
    0.43
    ਟ
    0.43
    де
    0.41
    від
    0.41
     وغیرہ
    0.41
    렌
    0.40
     متعلق
    0.40
    🠀
    0.39
    POSITIVE LOGITS
     ولكن
    0.44
     revolutionized
    0.43
     但是
    0.41
     থাম
    0.39
     এখন
    0.38
     becoming
    0.38
     HashTable
    0.38
    했지만
    0.38
     revolution
    0.37
     있지만
    0.37
    Activations Density 0.004%

    No Known Activations