© 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. 28725
    Prev
    Next
    INDEX
    Explanations

    peanut allergy testing

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

    insertion sort algorithms

    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
    ibhav
    0.47
    pril
    0.44
    かし
    0.44
    椁
    0.44
    ill
    0.42
     hurriedly
    0.41
    Mogo
    0.41
    緊急
    0.41
    ጊ
    0.41
    옻
    0.40
    POSITIVE LOGITS
     spun
    0.42
     naturali
    0.42
     khoan
    0.42
     Parte
    0.41
     spliced
    0.39
     Spinner
    0.39
     Insertion
    0.39
     AH
    0.38
     Repe
    0.38
     Sousa
    0.38
    Activations Density 0.006%

    No Known Activations