© 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. 73853
    Prev
    Next
    INDEX
    Explanations

    websites and online sources

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

    web links and addresses

    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
    ਤੀ
    0.49
    始まる
    0.49
    削除
    0.47
    ੁਰ
    0.47
    ਗੇ
    0.47
    ﻌ
    0.47
     वाली
    0.46
    ិច្
    0.46
    }=-
    0.46
    nements
    0.46
    POSITIVE LOGITS
     http
    0.63
     website
    0.61
     https
    0.59
     www
    0.59
     Flickr
    0.57
     Wikipedia
    0.53
     Google
    0.52
     wikipedia
    0.51
     DWI
    0.50
     Shutterstock
    0.49
    Activations Density 0.000%

    No Known Activations