© 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. 234910
    Prev
    Next
    INDEX
    Explanations

    Steinbeck's data cleaning

    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
     Nội
    0.49
    ran
    0.46
     Source
    0.46
    Source
    0.45
    Site
    0.44
    it
    0.43
    antec
    0.43
    源
    0.42
    Poke
    0.41
    h
    0.41
    POSITIVE LOGITS
     stric
    0.50
     ਕੀਤਾ
    0.48
    馥
    0.48
    かしい
    0.47
     divergents
    0.47
     ভিন্ন
    0.46
     dialed
    0.46
     боя
    0.46
    sounding
    0.46
    कत
    0.45
    Activations Density 0.001%

    No Known Activations