© 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. 189110
    Prev
    Next
    INDEX
    Explanations

    Introduction and context setters

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

    introduction or observation

    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
     moj
    0.51
    alf
    0.49
    gado
    0.48
    nią
    0.48
    nai
    0.47
    orkel
    0.47
    alamat
    0.47
    
    0.47
    YP
    0.46
    pisah
    0.46
    POSITIVE LOGITS
     Bells
    0.53
     Introduction
    0.47
     These
    0.46
     NORTH
    0.46
     considered
    0.45
     Adventure
    0.45
     INTRODUCTION
    0.45
     Cette
    0.44
     BELL
    0.44
     is
    0.43
    Activations Density 0.000%

    No Known Activations