© 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. 245640
    Prev
    Next
    INDEX
    Explanations

    you may/are/recognize

    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
     通勤
    0.55
    endige
    0.49
     清
    0.48
    essex
    0.48
     Bolog
    0.47
     potrebné
    0.47
     ==
    0.47
    bibli
    0.46
     WSL
    0.46
     desem
    0.46
    POSITIVE LOGITS
    Efficiency
    0.46
     الدین
    0.46
    лью
    0.46
    લ
    0.46
     manned
    0.45
    Motors
    0.45
    代目
    0.44
    از
    0.44
    즘
    0.44
    垚
    0.43
    Activations Density 0.001%

    No Known Activations