© 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. 206321
    Prev
    Next
    INDEX
    Explanations

    following a certain way

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

    while/or + it/a

    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
    RIG
    0.48
    的大小
    0.48
    OGR
    0.46
    
    0.46
    GMP
    0.45
    CONTENTS
    0.44
    
    0.44
    NEST
    0.44
    콴
    0.44
    SNAP
    0.43
    POSITIVE LOGITS
    ler
    0.47
     $\
    0.47
     "@{
    0.45
     ihrer
    0.45
    ale
    0.44
     »
    0.43
    ade
    0.43
    lere
    0.43
    angering
    0.43
    ere
    0.42
    Activations Density 0.002%

    No Known Activations