© 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. 16146
    Prev
    Next
    INDEX
    Explanations

    First, First off, Firstly

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

    first point introduction

    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
     altri
    0.49
    ?/
    0.48
     রি
    0.46
     również
    0.46
    后再
    0.46
    ?>
    0.45
    }/
    0.44
    \
    0.43
     både
    0.43
     তবু
    0.43
    POSITIVE LOGITS
     Secondly
    0.63
    槸
    0.60
     Öncelikle
    0.57
     secondly
    0.57
     Importantly
    0.52
    要知道
    0.52
    Secondly
    0.51
     хотелось
    0.51
     הם
    0.51
    是對
    0.48
    Activations Density 0.049%

    No Known Activations