© 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. 56959
    Prev
    Next
    INDEX
    Explanations

    specific technical contexts

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

    common logic

    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
     metaverse
    0.49
     esports
    0.48
     Esports
    0.46
     Molina
    0.46
     Metaverse
    0.46
     y
    0.46
     Holmes
    0.44
     Y
    0.43
     microwaves
    0.43
    \
    0.43
    POSITIVE LOGITS
     عادة
    0.50
     பெரும்பாலும்
    0.48
     Biasanya
    0.47
     ordinairement
    0.46
     Обычно
    0.45
    失敗
    0.44
    MyHomePage
    0.44
     repurchase
    0.44
     बहुतेक
    0.44
    ﻃ
    0.44
    Activations Density 0.000%

    No Known Activations