© 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. 52003
    Prev
    Next
    INDEX
    Explanations

    dog owner, gas pipelines, sales, chronograph

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

    multilingual concepts

    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
     Revival
    0.48
     /
    0.47
     Dressing
    0.46
     Insol
    0.46
     dressing
    0.46
     sword
    0.45
     store
    0.44
    ne
    0.44
     learnings
    0.44
     Collection
    0.43
    POSITIVE LOGITS
    LIM
    0.55
    追い
    0.50
    認証
    0.48
    პ
    0.48
    大きさ
    0.48
    PRF
    0.47
    国際
    0.47
    رود
    0.47
    ਮ
    0.46
    テレビ
    0.46
    Activations Density 0.000%

    No Known Activations