© 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. 181284
    Prev
    Next
    INDEX
    Explanations

    needs

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

    modelon-device services, models, chatbot

    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
    噹
    0.51
     ornate
    0.47
    ből
    0.46
    人
    0.46
    cri
    0.45
    结论
    0.44
     Fey
    0.44
     on
    0.43
    owego
    0.43
     const
    0.43
    POSITIVE LOGITS
     kerjasama
    0.49
    Massage
    0.45
    వచ్చు
    0.44
    ؟.
    0.44
     ภาษา
    0.44
    Honor
    0.44
    !।
    0.43
    䡏
    0.42
    ︡
    0.42
    HON
    0.42
    Activations Density 0.001%

    No Known Activations