© 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. 138947
    Prev
    Next
    INDEX
    Explanations

    listing something

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

    I will explain

    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
     日本製
    0.54
     技术
    0.52
    ặt
    0.52
     情報
    0.52
     तकनीकी
    0.51
     प्रशंस
    0.51
    プレイヤー
    0.50
    、$
    0.50
     осві
    0.50
    ショナル
    0.49
    POSITIVE LOGITS
    很久
    0.48
    Description
    0.47
    is
    0.47
    0.45
     AQU
    0.43
    Z
    0.43
     unconditionally
    0.43
    W
    0.43
    zka
    0.42
     unravel
    0.42
    Activations Density 0.001%

    No Known Activations