© 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. 23901
    Prev
    Next
    INDEX
    Explanations

    recipe instructions

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

    fermented foods like cabbage and kimchi

    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
    还没
    0.43
    唤
    0.43
    ců
    0.43
    וֹ
    0.42
    ვ
    0.42
    箩
    0.42
    ók
    0.42
    受伤
    0.42
    墾
    0.42
    தீ
    0.42
    POSITIVE LOGITS
     LLC
    0.48
    メソッド
    0.48
    の方法
    0.46
     実
    0.45
     By
    0.44
     Method
    0.43
     Aditya
    0.43
    Overwrite
    0.43
     mannen
    0.43
     Расійскай
    0.43
    Activations Density 0.009%

    No Known Activations