© 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. 173483
    Prev
    Next
    INDEX
    Explanations

    process, method, design

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

    process and system methods

    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
    nto
    0.51
    ŧ
    0.50
     فال
    0.49
     なり
    0.46
     Subsec
    0.46
     את
    0.46
    íg
    0.46
    ể
    0.46
     이르
    0.45
     своїх
    0.45
    POSITIVE LOGITS
    Process
    0.54
     Process
    0.54
    Method
    0.49
     Creme
    0.48
    ان
    0.47
     প্রক্রিয়া
    0.46
     proces
    0.46
    Design
    0.46
     Proses
    0.46
     Proces
    0.45
    Activations Density 0.002%

    No Known Activations