© 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. 128793
    Prev
    Next
    INDEX
    Explanations

    data protection

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

    Express.js inspired API

    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
     especiales
    0.45
    ່ຽ
    0.43
    mith
    0.43
     luckily
    0.42
    特
    0.42
    ifiz
    0.42
    לב
    0.41
    Luckily
    0.41
    elez
    0.41
     солдат
    0.41
    POSITIVE LOGITS
     বর্তমান
    0.45
     そ
    0.44
     saddhim
    0.43
    在庫
    0.42
     postérieurs
    0.41
    秏
    0.41
     取り
    0.41
     ০১
    0.41
     夕
    0.41
     考え
    0.40
    Activations Density 0.001%

    No Known Activations