© 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. 172250
    Prev
    Next
    INDEX
    Explanations

    discussion forum dates and intros

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

    instance variable

    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
    new
    0.44
     ruling
    0.42
    wikkel
    0.42
    1
    0.41
     info
    0.41
     new
    0.40
     groomed
    0.40
    info
    0.39
     nuevas
    0.39
     novos
    0.39
    POSITIVE LOGITS
     забруд
    0.53
    🐊
    0.53
     κάνει
    0.52
     atthakath
    0.52
     پانی
    0.52
     ট্যাঙ্ক
    0.52
     መድሃኒ
    0.51
     эт
    0.51
     সঞ্জীবনী
    0.50
     makeSound
    0.50
    Activations Density 0.000%

    No Known Activations