© 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. 12610
    Prev
    Next
    INDEX
    Explanations

    modify, format, purchase, communication, assets

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

    common and professional terms

    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
    0.57
    蟶
    0.53
    Methylsulfanyl
    0.52
    古墳
    0.52
    铍
    0.52
     drivetrain
    0.51
    Benzoimidazol
    0.50
    靂
    0.50
    䳕
    0.50
    >∕
    0.49
    POSITIVE LOGITS
    的
    0.90
    和
    0.71
    ：
    0.68
    的大
    0.66
    式
    0.65
    小
    0.64
    各
    0.63
    的小
    0.62
    或者
    0.61
    地址
    0.59
    Activations Density 0.010%

    No Known Activations