© 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. 68834
    Prev
    Next
    INDEX
    Explanations

    foreign language songs and contexts

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

    ordinal data and ranking

    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
    פ
    0.47
     premat
    0.46
    ಹೆ
    0.45
     exportation
    0.45
     incipient
    0.44
     seedlings
    0.44
     obstructive
    0.44
     spite
    0.43
    ]-\
    0.43
    ب
    0.43
    POSITIVE LOGITS
    აზე
    0.51
    ində
    0.47
    ście
    0.45
    indeki
    0.45
     मस्ती
    0.45
    ibli
    0.45
    了这个
    0.44
    ība
    0.43
    ider
    0.42
     Comedy
    0.42
    Activations Density 0.001%

    No Known Activations