© 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. 74066
    Prev
    Next
    INDEX
    Explanations

    childhood family stories

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

    title 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
     rubbed
    0.52
    лли
    0.49
    сса
    0.46
    доро
    0.46
     процен
    0.45
    ，
    0.45
    ра
    0.45
    тор
    0.45
    не
    0.44
    、
    0.44
    POSITIVE LOGITS
    หนด
    0.48
     মুছে
    0.46
     የቀ
    0.46
    (")
    0.46
     recounts
    0.45
     쭉
    0.45
    iosk
    0.44
     버튼
    0.43
     podcasts
    0.42
     იქ
    0.42
    Activations Density 0.001%

    No Known Activations