© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 117425
    Prev
    Next
    INDEX
    Explanations

    inter-Korean or legal contexts

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

    technical jargon and concepts

    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
    arsipkan
    0.47
    新增
    0.46
     स्वीकृति
    0.46
    reuung
    0.46
     ካ
    0.45
    審査
    0.45
    и
    0.45
     изда
    0.45
     које
    0.44
    }-$
    0.44
    POSITIVE LOGITS
     pluie
    0.52
     frosts
    0.50
     bicarbon
    0.50
     CRO
    0.49
     porosity
    0.48
     using
    0.47
     powders
    0.47
    )。
    0.47
     porch
    0.46
     porcelain
    0.46
    Activations Density 0.001%

    No Known Activations