© 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. 5050
    Prev
    Next
    INDEX
    Explanations

    The followed by specific description

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

    the ` ` ` ` code delimiter

    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
     :
    0.43
     moim
    0.42
     aihe
    0.41
     :"
    0.40
    :"
    0.40
    .
    0.38
     identified
    0.37
     ۔۔۔
    0.37
    :<
    0.36
     criando
    0.36
    POSITIVE LOGITS
    ließlich
    0.62
    cknowled
    0.60
     інших
    0.60
    此之外
    0.59
    yrıca
    0.58
    прочем
    0.57
    อื่นๆ
    0.54
     entanto
    0.54
     दूसरों
    0.50
     інші
    0.50
    Activations Density 0.121%

    No Known Activations