© 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. 5144
    Prev
    Next
    INDEX
    Explanations

    策劃, 轟烈, 往復, 维权, 滋潤, 治具

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

    cooking and spicy foods

    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
    鈮
    0.46
    Prothorax
    0.45
    獼
    0.43
    ೪
    0.42
    螓
    0.41
    Ethoxy
    0.41
    윕
    0.40
    𒊩
    0.39
    頎
    0.39
    ೮
    0.38
    POSITIVE LOGITS
    ↵↵
    0.39
    ，
    0.37
    出
    0.35
    、
    0.33
    出来
    0.32
    d
    0.32
    +
    0.32
    …
    0.31
    小
    0.30
    l
    0.29
    Activations Density 0.016%

    No Known Activations