© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23120
    Prev
    Next
    INDEX
    Explanations

    code blocks and mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.49
    Regular
    0.38
    Lond
    0.38
    Vacancy
    0.37
     ‘
    0.36
    MR
    0.36
    Sense
    0.35
    Keywords
    0.35
    ‘
    0.35
    نت
    0.35
    POSITIVE LOGITS
     ```
    0.81
     $$\
    0.74
    :<
    0.71
    ："
    0.64
    ：“
    0.64
    ```
    0.64
    如下
    0.63
     다음과
    0.61
     şöyle
    0.61
    :[
    0.59
    Activations Density 0.035%

    No Known Activations