© 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. 80565
    Prev
    Next
    INDEX
    Explanations

    blue case

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

    news, story, translate

    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
     البته
    0.48
    avgs
    0.48
    ())));
    0.46
    彩色
    0.46
    ‖</
    0.46
     Increment
    0.46
    τας
    0.45
    Increment
    0.45
    smtb
    0.45
    fontsize
    0.45
    POSITIVE LOGITS
     Ovaj
    0.45
     bureaucracy
    0.44
    rió
    0.44
     Contracts
    0.44
    潾
    0.44
     memoir
    0.44
    ра
    0.43
     suspicion
    0.43
     TikTok
    0.42
     cheap
    0.42
    Activations Density 0.000%

    No Known Activations