© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 191
    Prev
    Next
    INDEX
    Explanations

    tikz latex code

    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
     स्किप
    0.38
     bathrooms
    0.38
    둰
    0.38
    MessageNow
    0.37
    厠
    0.36
     restrooms
    0.36
     జరిగిన
    0.35
    нена
    0.35
     स्व
    0.34
    
    0.34
    POSITIVE LOGITS
    1
    0.42
    7
    0.39
     ){
    0.38
    6
    0.38
    po
    0.38
    ic
    0.37
    9
    0.37
    vi
    0.37
    AMA
    0.36
    ){
    0.36
    Activations Density 0.000%

    No Known Activations